Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28937
    Prev
    Next
    INDEX
    Explanations

    numeric and structural representations in various contexts

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    156
    +0.53
    4.2%
    111
    +0.51
    4.0%
    333
    +0.10
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.53
    0.53
    4
    +0.51
    0.52
    111
    +0.10
    0.50
    Negative Logits
    inations
    -1.19
    jour
    -1.16
    lam
    -1.15
     covert
    -1.15
    ↵↵          
    -1.13
    ↵↵                                         
    -1.13
     ↵    
    -1.13
    ↵                                          
    -1.13
    <|outofrange|>
    -1.13
    <|outofrange|>
    -1.13
    POSITIVE LOGITS
    "}](#
    1.49
    ^](#
    1.22
    creas
    1.19
    USY
    1.18
     receptor
    1.18
    ISHED
    1.15
    emia
    1.14
    ,{{\
    1.13
    otrophic
    1.11
    cester
    1.10
    Activations Density 1.232%

    No Known Activations