© 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. 12899
    Prev
    Next
    INDEX
    Explanations

    questions or wonderings

    oai_token-act-pair · gpt-3.5-turbo

    questions starting with "how" or "why."

    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
    catentry
    -0.87
    breaking
    -0.82
    arget
    -0.81
    20439
    -0.79
    alde
    -0.79
    ipment
    -0.75
    grab
    -0.74
    rim
    -0.73
    utf
    -0.73
    ovych
    -0.73
    POSITIVE LOGITS
     exactly
    0.77
     pige
    0.77
     anyone
    0.73
     anybody
    0.72
     adequ
    0.66
     conceivable
    0.65
     feasible
    0.65
     vain
    0.65
    ?".
    0.64
     why
    0.63
    Activations Density 0.153%

    No Known Activations