© 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. 2-RES-SM
    11. 10571
    Prev
    Next
    INDEX
    Explanations

    URLs, specifically those related to GitHub

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    500
    +0.15
    0.8%
    28
    +0.14
    0.8%
    243
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.15
    0.03
    28
    +0.14
    0.03
    500
    +0.11
    0.03
    Negative Logits
    ulous
    -1.67
    ired
    -1.60
    born
    -1.49
     Va
    -1.49
    ophageal
    -1.49
    quin
    -1.44
    leading
    -1.44
    vous
    -1.44
    xiety
    -1.40
    izing
    -1.40
    POSITIVE LOGITS
    İ
    1.51
     ur
    1.48
    ľĵ
    1.48
     ore
    1.46
    doi
    1.43
    www
    1.43
    Į
    1.43
     archives
    1.42
    ://
    1.42
     sale
    1.42
    Activations Density 0.044%

    No Known Activations