© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 24227
    Prev
    Next
    INDEX
    Explanations

    web related terms such as "Website" and "Visit" in text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of websites and online information

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    DN
    -0.70
    rament
    -0.63
     pickups
    -0.61
    picking
    -0.60
    GBT
    -0.57
     nationally
    -0.57
    nered
    -0.56
    gling
    -0.56
     sounding
    -0.55
     impending
    -0.54
    POSITIVE LOGITS
     Flavoring
    0.67
     Gutenberg
    0.61
    anasia
    0.61
    agy
    0.60
    izen
    0.60
    ugi
    0.60
    fal
    0.60
     Thumbnails
    0.59
    ichita
    0.57
    close
    0.57
    Activations Density 0.020%

    No Known Activations