© 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. 4-RES-SM
    11. 14798
    Prev
    Next
    INDEX
    Explanations

    lines of code or programming-related statements

    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
    156
    +0.47
    3.3%
    111
    +0.44
    3.1%
    98
    +0.16
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.47
    0.77
    156
    +0.44
    0.53
    71
    +0.16
    0.55
    Negative Logits
    ī
    -4.59
    Ī
    -4.58
    ↵↵
    -4.53
    -4.53
    ↵↵
    -4.53
    -4.53
    <|outofrange|>
    -4.53
    ↵
    -4.53
     ↵
    -4.53
    ↵
    -4.53
    POSITIVE LOGITS
    olia
    1.51
     them
    1.47
    iorari
    1.44
     whatever
    1.41
    ao
    1.34
    ison
    1.33
    them
    1.29
     everything
    1.29
     us
    1.27
    scriptions
    1.23
    Activations Density 0.810%

    No Known Activations