© 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. 13047
    Prev
    Next
    INDEX
    Explanations

    sentences indicating a call to action

    oai_token-act-pair · gpt-3.5-turbo

    punctuated sentences or statements in a text

    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
     tremend
    -0.85
    icz
    -0.84
     charact
    -0.83
     oun
    -0.80
     carbohyd
    -0.75
     satell
    -0.73
     mosqu
    -0.72
    ãĥ¢
    -0.71
     fermented
    -0.71
     confir
    -0.70
    POSITIVE LOGITS
     Includes
    1.47
     Also
    1.44
     Including
    1.29
     Especially
    1.24
     Allows
    1.24
     Typically
    1.18
     Usually
    1.18
     Useful
    1.18
     Currently
    1.17
     Contains
    1.17
    Activations Density 0.423%

    No Known Activations