© 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. 24322
    Prev
    Next
    INDEX
    Explanations

    references to grace and related concepts

    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
    43
    +0.14
    0.8%
    258
    +0.12
    0.7%
    156
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.11
    156
    +0.12
    0.06
    271
    +0.11
    0.04
    Negative Logits
    ¿½
    -3.84
    ĨĴ
    -3.61
    ĻĤ
    -3.36
    ĵ
    -3.36
    Ĭ
    -3.34
    Ħ
    -3.19
    ĥ½
    -3.17
    ı
    -3.15
    ¥
    -3.14
    Ĥ
    -3.07
    POSITIVE LOGITS
    holder
    2.44
    maker
    1.94
    holders
    1.82
     versa
    1.82
    grounds
    1.79
    wall
    1.66
    pere
    1.63
    keeper
    1.63
    makers
    1.60
    walls
    1.59
    Activations Density 0.435%

    No Known Activations