© 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. 28657
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "of" and related frequency in phrases

    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
    288
    +0.12
    0.6%
    238
    +0.12
    0.6%
    87
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.12
    0.03
    249
    +0.12
    0.03
    457
    +0.11
    0.04
    Negative Logits
    £
    -2.09
    ´
    -2.07
    º
    -2.00
    ³
    -2.00
    Ľ
    -1.99
    ĻĤ
    -1.97
    ĭ
    -1.94
    Ł
    -1.93
    »
    -1.91
    »¿
    -1.89
    POSITIVE LOGITS
    ches
    1.71
    ials
    1.59
    itals
    1.50
     '\
    1.49
    olars
    1.46
    ality
    1.46
     characters
    1.44
     keys
    1.44
     Figures
    1.42
     figures
    1.41
    Activations Density 0.746%

    No Known Activations