© 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. 11331
    Prev
    Next
    INDEX
    Explanations

    objects or creatures typically associated with specific situations or actions

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns or objects that evoke imagery or represent themes in the text

    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
     Procedures
    -0.86
     Reps
    -0.84
     Goals
    -0.83
     venues
    -0.82
     Statements
    -0.82
     independents
    -0.81
     Events
    -0.81
     demographics
    -0.80
     assessments
    -0.80
     scenarios
    -0.80
    POSITIVE LOGITS
     shaped
    1.13
    pipe
    1.11
    shaped
    1.03
    hole
    1.00
    fish
    1.00
    brush
    0.99
    tailed
    0.99
    cake
    0.97
    cone
    0.97
    headed
    0.94
    Activations Density 0.372%

    No Known Activations