© 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. 14171
    Prev
    Next
    INDEX
    Explanations

    imperative statements in technical contexts

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and introductory phrases to present information or instructions

    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
    .","
    -0.78
    .</
    -0.72
     ..."
    -0.64
     thereto
    -0.62
     swe
    -0.61
    )</
    -0.60
    —"
    -0.60
    court
    -0.59
     âĢ¦"
    -0.58
    -"
    -0.58
    POSITIVE LOGITS
    odore
    1.11
    resa
    1.08
    notations
    1.00
    wards
    0.94
     Conclusion
    0.94
    mosp
    0.93
    bidden
    0.92
    chieve
    0.91
    iple
    0.89
     Contents
    0.87
    Activations Density 0.413%

    No Known Activations