© 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. 14714
    Prev
    Next
    INDEX
    Explanations

    references to legal jurisdictions and court systems

    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
    337
    +0.11
    0.6%
    149
    +0.10
    0.6%
    157
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    364
    +0.11
    0.02
    202
    +0.10
    0.01
    57
    +0.10
    0.02
    Negative Logits
    oretic
    -1.69
     them
    -1.66
     thereof
    -1.58
    ycler
    -1.44
     cassette
    -1.43
    ÅĦ
    -1.42
     readings
    -1.40
    ificates
    -1.39
     standard
    -1.39
    ène
    -1.36
    POSITIVE LOGITS
    Ģ
    2.86
    ĻĤ
    2.69
     TEXAS
    2.69
    ®
    2.52
    ı
    2.50
    ¶
    2.48
    ĩ
    2.48
    ½
    2.44
    ¸
    2.40
     APPEALS
    2.39
    Activations Density 0.058%

    No Known Activations