© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 25355
    Prev
    Next
    INDEX
    Explanations

    terms related to biochemical binding or interactions

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    376
    +0.14
    0.8%
    148
    +0.12
    0.7%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.04
    156
    +0.12
    0.03
    271
    +0.12
    0.01
    Negative Logits
    ¸
    -2.57
    ´
    -2.34
    ³
    -2.33
    ½
    -2.29
    ²
    -2.27
    -2.27
    -2.27
    <|outofrange|>
    -2.27
    č↵
    -2.27
    ↵
    -2.27
    POSITIVE LOGITS
     capacity
    1.79
     molecules
    1.66
     proteins
    1.63
     areas
    1.61
     regulators
    1.59
    eners
    1.57
     ---
    1.57
    ently
    1.56
     element
    1.54
     mechanism
    1.53
    Activations Density 0.166%

    No Known Activations