© 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. 8-RES-JB
    11. 14318
    Prev
    Next
    INDEX
    Explanations

    numerical figures in the format of '1 X' where X ranges from the single digit to a double-digit number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number "1" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    enges
    -0.62
     histories
    -0.61
     mascul
    -0.61
     Pompe
    -0.59
     hygiene
    -0.57
    awaru
    -0.57
    olds
    -0.57
    orative
    -0.56
    birds
    -0.56
     Lumpur
    -0.55
    POSITIVE LOGITS
    st
    1.31
    Password
    1.30
    125
    1.25
    120
    1.21
    000000
    1.06
    ½
    1.05
    128
    1.02
    123
    0.96
    âģ
    0.95
    0000000
    0.87
    Activations Density 0.103%

    No Known Activations