© 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. 4-RES-SM
    11. 9010
    Prev
    Next
    INDEX
    Explanations

    references to various institutions and organizations

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    348
    +0.14
    0.8%
    78
    +0.13
    0.7%
    483
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.14
    0.03
    305
    +0.13
    0.04
    168
    +0.12
    0.05
    Negative Logits
    Ł
    -2.59
    ¯
    -2.42
    ľ
    -2.16
    ©
    -2.15
    Ŀ
    -2.11
    ł
    -2.06
    ¦
    -2.02
    ļ
    -2.00
    ľĵ
    -2.00
    Ń
    -1.91
    POSITIVE LOGITS
     of
    2.51
     Of
    2.05
     Against
    1.95
     Nacional
    1.84
     Building
    1.78
     Award
    1.78
     Islands
    1.73
    Of
    1.72
     Committee
    1.72
    hold
    1.71
    Activations Density 0.447%

    No Known Activations