© 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. 13691
    Prev
    Next
    INDEX
    Explanations

    references to legal or social justice issues

    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
    400
    +0.15
    0.8%
    417
    +0.11
    0.6%
    274
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    400
    +0.15
    -0.00
    264
    +0.11
    0.11
    88
    +0.10
    0.02
    Negative Logits
     ^[@
    -4.31
    '?"
    -4.09
    '."
    -3.77
    ?'
    -3.53
    '.
    -3.48
    ...'
    -3.45
    ^[@
    -3.41
    ,'"
    -3.40
    .'
    -3.37
    ,'
    -3.34
    POSITIVE LOGITS
     “
    7.82
     “[
    6.57
     ”
    5.56
     (“
    5.30
    “
    5.26
    ”
    4.92
    .“
    4.76
    “[
    4.75
     ‘
    4.71
    .”
    4.58
    Activations Density 7.285%

    No Known Activations