© 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. 2-RES-SM
    11. 9699
    Prev
    Next
    INDEX
    Explanations

    references to "man" or gender-related terms

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    410
    +0.16
    0.9%
    73
    +0.13
    0.7%
    407
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.16
    0.04
    73
    +0.13
    0.03
    191
    +0.11
    0.04
    Negative Logits
    ĥ
    -1.69
    ľĵ
    -1.59
     recipients
    -1.54
    ļ
    -1.53
    ÑģÑĤÑĮ
    -1.50
     lower
    -1.41
    orthy
    -1.40
    Ŀ
    -1.38
    IJ
    -1.38
     importance
    -1.38
    POSITIVE LOGITS
    hattan
    2.91
    uscript
    2.77
    ifest
    2.50
    ifold
    2.23
    fred
    2.13
    uel
    2.08
    nered
    2.05
    agment
    1.97
    oe
    1.95
    ufact
    1.91
    Activations Density 0.192%

    No Known Activations