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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 11675
    Prev
    Next
    INDEX
    Explanations

    mentions of amino acids or related compounds

    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
    129
    +0.16
    0.9%
    463
    +0.11
    0.6%
    327
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.16
    0.02
    66
    +0.11
    0.02
    271
    +0.11
    0.00
    Negative Logits
    rive
    -1.61
     success
    -1.61
     else
    -1.61
     promise
    -1.53
     nesting
    -1.49
    fiddle
    -1.46
     scene
    -1.46
    matically
    -1.45
    pez
    -1.45
     successful
    -1.42
    POSITIVE LOGITS
    ¢
    1.97
    «
    1.95
    aris
    1.87
    ħ
    1.78
    ¤
    1.74
    owitz
    1.74
    aldehyde
    1.69
    stein
    1.69
    glycer
    1.69
    ¨
    1.68
    Activations Density 0.124%

    No Known Activations