© 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. 25510
    Prev
    Next
    INDEX
    Explanations

    terms associated with modulation, inhibition, and regulation in biological processes

    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
    23
    +0.26
    1.5%
    156
    +0.24
    1.4%
    376
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    400
    +0.26
    0.02
    376
    +0.24
    0.02
    148
    +0.17
    0.02
    Negative Logits
    esan
    -1.88
    PROM
    -1.69
     champ
    -1.63
    liche
    -1.61
    urer
    -1.60
    endor
    -1.59
    sburg
    -1.57
    ilage
    -1.57
    illard
    -1.54
    Metrics
    -1.52
    POSITIVE LOGITS
    ĻĤ
    4.85
    ľĵ
    4.50
    ¥
    4.46
    Ļª
    4.38
    Ĥ¬
    4.37
    ¿
    4.33
    ł
    4.27
    ľ
    4.26
    ĺ
    4.24
    Ļ
    4.24
    Activations Density 0.134%

    No Known Activations