© 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 EvalsExportsAPI 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. 20418
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislative bodies or specific government institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative bodies and voting processes

    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
    seeing
    -0.73
     prey
    -0.68
     pedestrians
    -0.68
     squats
    -0.65
    laus
    -0.62
    rower
    -0.61
    itness
    -0.61
     bicycl
    -0.61
     perceived
    -0.60
    acca
    -0.60
    POSITIVE LOGITS
     shelves
    0.81
     sometime
    0.78
     coffers
    0.75
     Marketplace
    0.72
     archives
    0.72
    Store
    0.72
     auction
    0.71
     marketplace
    0.71
    ebin
    0.70
     ASAP
    0.69
    Activations Density 0.609%

    No Known Activations