© 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. 1-RES-SM
    11. 29881
    Prev
    Next
    INDEX
    Explanations

    end punctuation marks at the end of sentences

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    23
    +0.13
    0.7%
    100
    +0.13
    0.7%
    258
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.13
    0.04
    133
    +0.13
    0.03
    107
    +0.13
    0.04
    Negative Logits
    "}](#
    -2.08
    wer
    -1.64
    opter
    -1.63
    rance
    -1.61
    lot
    -1.57
    tone
    -1.56
     hereto
    -1.53
    inux
    -1.50
    wagen
    -1.49
    olt
    -1.48
    POSITIVE LOGITS
    ³
    3.85
    Į
    3.83
    ĥ
    3.65
    ®
    3.60
    Ĭ
    3.57
    Ĩ
    3.57
    ´
    3.52
    Ŀ
    3.52
    Ī
    3.49
    ĥ½
    3.48
    Activations Density 0.263%

    No Known Activations