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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 29717
    Prev
    Next
    INDEX
    Explanations

    programming-related environments and configurations

    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
    221
    +0.11
    0.6%
    450
    +0.11
    0.6%
    73
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.11
    0.01
    163
    +0.11
    0.01
    379
    +0.10
    0.02
    Negative Logits
    ↵                 
    -1.90
     ↵     
    -1.90
    <|outofrange|>
    -1.90
    <|outofrange|>
    -1.90
                                              
    -1.90
              ↵ 
    -1.90
                                                                                 
    -1.90
                             
    -1.90
    ↵                              
    -1.90
           ↵ 
    -1.90
    POSITIVE LOGITS
    liness
    1.45
    language
    1.44
    iousness
    1.43
     Field
    1.41
     tense
    1.41
     language
    1.39
    VERTISEMENT
    1.38
     clenched
    1.38
     Language
    1.38
     cookies
    1.37
    Activations Density 0.097%

    No Known Activations