© 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 EvalsExportsAPI 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. 10685
    Prev
    Next
    INDEX
    Explanations

    references to software licensing and usage terms

    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
    190
    +0.15
    0.9%
    294
    +0.12
    0.7%
    136
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    190
    +0.15
    0.04
    359
    +0.12
    0.04
    445
    +0.11
    0.03
    Negative Logits
    ķ
    -1.71
    ĥ½
    -1.64
    ľĵ
    -1.56
    ĩ
    -1.54
    ¼
    -1.49
    oretic
    -1.48
    ·¸
    -1.47
     Nile
    -1.45
    ¢
    -1.44
    rait
    -1.43
    POSITIVE LOGITS
     unless
    2.09
    .<
    1.73
     except
    1.69
    ._
    1.62
    .</
    1.60
    .
    1.57
    ){#
    1.53
    ом
    1.53
    .).
    1.53
    _.
    1.52
    Activations Density 0.166%

    No Known Activations