© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8621
    Prev
    Next
    INDEX
    Explanations

    phrases indicating legal disclaimers or conditions, particularly those mentioning warranties and liabilities

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    78
    +0.19
    1.2%
    271
    +0.13
    0.8%
    107
    +0.10
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    280
    +0.19
    0.01
    441
    +0.13
    0.01
    273
    +0.10
    0.01
    Negative Logits
    =”
    -1.53
    azine
    -1.53
    able
    -1.39
    agne
    -1.30
    respond
    -1.28
    amphetamine
    -1.27
    :&
    -1.27
    umab
    -1.25
    ically
    -1.24
    articles
    -1.22
    POSITIVE LOGITS
    Ľ
    3.38
    į
    3.11
    ±
    3.04
    ©
    3.03
    Ŀ
    3.02
    Ħ
    3.01
    «
    2.98
    ¬
    2.98
    ī
    2.98
    ħ
    2.97
    Activations Density 0.051%

    No Known Activations