© 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 EvalsExportsAPI 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. 13346
    Prev
    Next
    INDEX
    Explanations

    references to external stylesheets or CSS in a document

    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
    +0.15
    0.8%
    431
    +0.14
    0.8%
    340
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.15
    0.06
    195
    +0.14
    0.06
    500
    +0.13
    0.04
    Negative Logits
     respondent
    -1.54
    ","
    -1.46
     herself
    -1.40
     petitioners
    -1.39
    ,[@
    -1.34
    aban
    -1.30
    uan
    -1.27
    isten
    -1.26
    ,”
    -1.26
    ħ
    -1.25
    POSITIVE LOGITS
     <
    5.91
     </
    4.89
     >
    4.68
    <
    4.62
    >
    4.14
    .<
    4.03
    </
    4.02
    .</
    3.87
    >\
    3.79
    <\
    3.76
    Activations Density 0.911%

    No Known Activations