© 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. 14214
    Prev
    Next
    INDEX
    Explanations

    information related to locations, specifically mentioning Long Island

    oai_token-act-pair · gpt-3.5-turbo

    key phrases related to public safety and guidelines

    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
    ).[
    -0.80
     nonetheless
    -0.77
    .).
    -0.73
    ."[
    -0.62
     nevertheless
    -0.62
    ).
    -0.56
    .")
    -0.56
    ]."
    -0.55
    ").
    -0.54
    ".[
    -0.53
    POSITIVE LOGITS
    ?'
    0.75
    ?",
    0.70
    ':
    0.68
    ?:
    0.65
    .?
    0.61
    '?
    0.61
    itialized
    0.56
     ?
    0.56
     \'
    0.55
     ',
    0.54
    Activations Density 1.813%

    No Known Activations