© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 10194
    Prev
    Next
    INDEX
    Explanations

    specific types of entities or objects within various contexts, such as birds, fish, cables, and floral arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    21
    +0.38
    2.4%
    156
    +0.27
    1.7%
    186
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.38
    0.11
    401
    +0.27
    0.07
    117
    +0.14
    0.12
    Negative Logits
    <|outofrange|>
    -6.64
    ↵                                     
    -6.64
    <|outofrange|>
    -6.64
    ↵  
    -6.64
                                                                                                                                    
    -6.64
                                                               
    -6.64
    ↵↵                   
    -6.64
    ↵                                              
    -6.64
    č↵                   
    -6.64
    <|outofrange|>
    -6.64
    POSITIVE LOGITS
    hip
    2.69
    hips
    2.25
    ystems
    2.16
     themselves
    2.13
    ource
    2.00
    heet
    1.95
    hot
    1.91
    elf
    1.91
    pace
    1.87
    helf
    1.84
    Activations Density 1.344%

    No Known Activations