© 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. 24794
    Prev
    Next
    INDEX
    Explanations

    references to courts and legal proceedings

    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
    184
    +0.15
    0.8%
    434
    +0.14
    0.8%
    158
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    158
    +0.15
    0.01
    364
    +0.14
    0.02
    434
    +0.13
    0.01
    Negative Logits
     outgoing
    -1.63
     {}
    -1.57
     difference
    -1.56
     inward
    -1.52
     tail
    -1.50
    )](#
    -1.47
    enig
    -1.41
    ky
    -1.41
    utz
    -1.41
     connection
    -1.39
    POSITIVE LOGITS
    ¼
    2.50
    »¿
    2.40
    Ĩ
    2.20
    Ń
    2.05
    ŀ
    2.02
    ¤
    2.00
    ī
    1.99
    Ĭ
    1.91
    ĭ
    1.86
    cias
    1.86
    Activations Density 0.104%

    No Known Activations