© 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. 1140
    Prev
    Next
    INDEX
    Explanations

    references to fireworks

    oai_token-act-pair · gpt-3.5-turbo

    references to fireworks and clowns

    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
    à©
    -0.86
    lessly
    -0.76
    à¨
    -0.73
    bern
    -0.71
    ovo
    -0.69
     Borders
    -0.66
    ient
    -0.65
     Governments
    -0.65
    inion
    -0.65
     Delete
    -0.64
    POSITIVE LOGITS
     spectacle
    0.94
     amuse
    0.89
     exhib
    0.88
     displays
    0.84
     display
    0.83
     fireworks
    0.80
    oons
    0.80
     festivities
    0.79
     exhibitions
    0.79
     sightings
    0.79
    Activations Density 0.095%

    No Known Activations