Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27014
    Prev
    Next
    INDEX
    Explanations

    references to medical or scientific examinations and studies

    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
    156
    +0.16
    0.9%
    173
    +0.12
    0.7%
    131
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.16
    0.02
    100
    +0.12
    0.02
    281
    +0.11
    0.02
    Negative Logits
    IJ
    -2.56
    §
    -2.50
    Ĵ
    -2.40
    Į
    -2.37
    ŀ
    -2.35
    ĥ½
    -2.17
    ī
    -2.06
    Ĭ
    -2.00
    ¥
    -2.00
    ķ
    -1.98
    POSITIVE LOGITS
    etric
    1.89
    staff
    1.78
    ary
    1.71
    grade
    1.68
    al
    1.67
    matically
    1.61
    iece
    1.60
    iners
    1.60
    rade
    1.50
    stick
    1.48
    Activations Density 0.084%

    No Known Activations