© 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. 27120
    Prev
    Next
    INDEX
    Explanations

    references to domestic violence and abuse

    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
    246
    +0.14
    0.8%
    304
    +0.12
    0.7%
    37
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    37
    +0.14
    0.01
    29
    +0.12
    0.01
    304
    +0.12
    0.02
    Negative Logits
     opaque
    -1.76
    Ļª
    -1.66
     gonna
    -1.62
    ĨĴ
    -1.59
    visible
    -1.45
    elijk
    -1.43
     surjective
    -1.42
    Ĥ¬
    -1.41
     explicitly
    -1.38
     scratch
    -1.34
    POSITIVE LOGITS
    erre
    1.73
    rends
    1.57
    ation
    1.54
    emen
    1.53
    uty
    1.46
    Decided
    1.46
    anden
    1.44
    ror
    1.42
    eLife
    1.41
    dess
    1.39
    Activations Density 0.194%

    No Known Activations