© 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. 1-RES-SM
    11. 28149
    Prev
    Next
    INDEX
    Explanations

    indefinite articles and their frequency in the text

    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
    98
    +0.19
    1.1%
    478
    +0.17
    1.0%
    342
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.19
    0.06
    500
    +0.17
    0.06
    342
    +0.13
    0.06
    Negative Logits
    lessness
    -2.00
    itures
    -1.80
    ÅĽÄĩ
    -1.72
    ictions
    -1.69
    isc
    -1.63
    rooms
    -1.61
     coff
    -1.60
    iscus
    -1.57
     attention
    -1.55
    orro
    -1.54
    POSITIVE LOGITS
    Ŀ
    2.72
    ĸ
    2.46
    ĭ
    2.46
    Ĵ
    2.40
    Ĩ
    2.40
    ¾
    2.38
    ĸ´
    2.38
    ĵ
    2.33
    ĥ
    2.32
    Ł
    2.28
    Activations Density 0.443%

    No Known Activations