© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 20414
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Ath" or "Athlon"

    oai_token-act-pair · gpt-3.5-turbo

    references to athletic events or athletes, particularly related to marathons

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Charge
    -0.81
     externalToEVAOnly
    -0.78
    INTER
    -0.73
    ITED
    -0.73
    Micro
    -0.70
    BOX
    -0.69
    ding
    -0.68
    æĸ¹
    -0.67
    PLA
    -0.67
    CDC
    -0.66
    POSITIVE LOGITS
     Ath
    1.15
    onite
    1.06
    lete
    0.99
     Creed
    0.96
    oton
    0.93
    saf
    0.88
    thur
    0.87
    izoph
    0.85
    assi
    0.85
    arus
    0.85
    Activations Density 0.013%

    No Known Activations