© 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. 14032
    Prev
    Next
    INDEX
    Explanations

    references to court cases 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/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
    255
    +0.14
    0.9%
    21
    +0.13
    0.8%
    237
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    237
    +0.14
    0.01
    27
    +0.13
    0.01
    126
    +0.11
    0.00
    Negative Logits
     Nobel
    -1.29
    cip
    -1.28
     addict
    -1.27
     aut
    -1.25
     surviving
    -1.24
     pars
    -1.23
     ordinary
    -1.21
     organ
    -1.21
    enzyme
    -1.21
     arte
    -1.21
    POSITIVE LOGITS
    Į
    2.25
    ĥ
    1.96
    ĸ
    1.95
    ¸
    1.93
    Ĩ
    1.93
    ¹
    1.90
    ī
    1.89
    ĺ
    1.87
    ı
    1.87
    ¬
    1.85
    Activations Density 0.018%

    No Known Activations