© 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. 29093
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
    185
    +0.13
    0.7%
    465
    +0.12
    0.7%
    498
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.28
    156
    +0.12
    0.13
    271
    +0.11
    0.14
    Negative Logits
    UIT
    -1.48
    issues
    -1.48
     privacy
    -1.44
    Web
    -1.42
     Web
    -1.41
     shelf
    -1.40
     skirts
    -1.38
    browser
    -1.38
    "--
    -1.38
    Board
    -1.37
    POSITIVE LOGITS
    ī
    2.71
    Ń
    2.32
    Ŀ
    2.27
    ¬
    2.22
    ĵ
    2.19
    ¨
    2.12
    ĩ
    2.12
    ĥ
    2.12
    ¦
    2.09
    »
    2.08
    Activations Density 0.200%

    No Known Activations