© 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. 4-RES-SM
    11. 13626
    Prev
    Next
    INDEX
    Explanations

    specific characters and symbols used in programming or markup languages

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    156
    +0.35
    2.1%
    466
    +0.14
    0.8%
    325
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.35
    0.04
    325
    +0.14
    0.06
    203
    +0.12
    0.03
    Negative Logits
     thereof
    -1.45
     equipment
    -1.44
    antry
    -1.44
     performer
    -1.42
    opause
    -1.37
    hesis
    -1.33
     accuracy
    -1.31
     illness
    -1.30
    inates
    -1.30
    walks
    -1.28
    POSITIVE LOGITS
    ľ
    3.99
    ¦
    3.96
    ¼
    3.93
    Ĵ
    3.87
    ĸ
    3.80
    Ĩ
    3.73
    ·
    3.70
    ļ
    3.68
    ¹
    3.67
    ½
    3.63
    Activations Density 0.284%

    No Known Activations