© 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. 14934
    Prev
    Next
    INDEX
    Explanations

    descriptions of preferences or likes

    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
    25
    +0.20
    1.1%
    150
    +0.11
    0.6%
    361
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.20
    0.05
    156
    +0.11
    0.04
    510
    +0.11
    0.04
    Negative Logits
    ĥ
    -3.60
    ¿½
    -3.59
    ¯
    -3.49
    ·
    -3.49
    FFIRMED
    -3.44
         ↵
    -3.44
    -3.44
    ↵
    -3.44
    ↵
    -3.44
    <|outofrange|>
    -3.44
    POSITIVE LOGITS
     to
    2.52
     something
    1.96
     someone
    1.88
     answers
    1.83
     TO
    1.81
     them
    1.77
     somebody
    1.76
    lessly
    1.74
     permission
    1.72
     him
    1.71
    Activations Density 0.163%

    No Known Activations