© 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. 9155
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or symbols related to scientific equations

    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
    21
    +0.22
    1.2%
    271
    +0.15
    0.9%
    172
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    333
    +0.22
    0.02
    448
    +0.15
    0.02
    21
    +0.12
    0.01
    Negative Logits
     question
    -1.61
     information
    -1.56
     applies
    -1.55
     accord
    -1.51
     kind
    -1.50
     somewhere
    -1.48
     confirmation
    -1.46
     combination
    -1.45
     questions
    -1.43
     sort
    -1.42
    POSITIVE LOGITS
    ¨
    3.94
    ¡
    3.91
    3.77
    ↵
    3.77
    č↵
    3.77
    3.77
    3.77
    ↵
    3.77
    3.77
    <|outofrange|>
    3.77
    Activations Density 0.107%

    No Known Activations