© 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. 25421
    Prev
    Next
    INDEX
    Explanations

    references to numerical data or statistics

    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
    396
    +0.19
    1.1%
    100
    +0.13
    0.7%
    458
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.19
    0.04
    396
    +0.13
    0.04
    436
    +0.12
    0.04
    Negative Logits
    hand
    -1.57
     responsibility
    -1.52
    respons
    -1.51
     another
    -1.50
    efficacy
    -1.50
     offense
    -1.48
     terrorism
    -1.47
     reliance
    -1.46
    responsible
    -1.45
     hatred
    -1.45
    POSITIVE LOGITS
    ·¸
    3.09
    ¤
    2.93
    ³
    2.86
    £
    2.80
    ħ
    2.78
    İ
    2.75
    į
    2.71
    ¯
    2.67
    ĥ½
    2.67
    º
    2.62
    Activations Density 0.095%

    No Known Activations