© 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. 9038
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and references in programming documentation

    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
    +0.20
    1.1%
    47
    +0.18
    1.0%
    78
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.20
    0.05
    298
    +0.18
    0.03
    78
    +0.16
    0.00
    Negative Logits
    ’.
    -3.57
    .’
    -3.13
    ’,
    -2.93
    !’
    -2.53
    ,’
    -2.45
    ?’
    -2.43
    .[]{
    -2.40
    '.
    -2.33
    .’”
    -2.16
    .',
    -2.16
    POSITIVE LOGITS
    "
    3.40
    ")
    2.94
    "`
    2.66
    "))
    2.52
    )"
    2.42
    "){
    2.36
    "])
    2.29
    ()"
    2.27
    ").
    2.26
    "[
    2.12
    Activations Density 0.247%

    No Known Activations