© 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. 1-RES-SM
    11. 28976
    Prev
    Next
    INDEX
    Explanations

    instances of negation or refusal in statements or claims

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    346
    +0.14
    0.8%
    290
    +0.14
    0.8%
    181
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.14
    0.05
    346
    +0.14
    0.02
    290
    +0.11
    0.07
    Negative Logits
    azzo
    -1.81
    itage
    -1.65
    ubert
    -1.64
    odies
    -1.62
    coe
    -1.56
    ELD
    -1.54
    itatively
    -1.53
    braska
    -1.52
    assed
    -1.52
    selves
    -1.51
    POSITIVE LOGITS
    ¥
    2.46
    »¿
    2.46
    ¾
    2.45
    ĸ´
    2.44
    £
    2.40
    ½
    2.40
    ĸ
    2.37
    ¢
    2.36
    Ł
    2.34
    ¿
    2.28
    Activations Density 1.628%

    No Known Activations