© 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. 11564
    Prev
    Next
    INDEX
    Explanations

    information related to car accidents and law enforcement actions

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of vehicles and driving-related incidents

    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
    pora
    -0.90
     diplom
    -0.81
    olars
    -0.78
    beard
    -0.73
    dds
    -0.72
    piece
    -0.69
    awaru
    -0.68
     enshr
    -0.68
     priests
    -0.67
    Arch
    -0.67
    POSITIVE LOGITS
     Interstate
    1.14
     parked
    1.07
     Highway
    1.07
     traffic
    1.02
     lanes
    1.01
     driveway
    1.00
     pedestrians
    1.00
     Traffic
    0.98
     brakes
    0.97
     headlights
    0.97
    Activations Density 0.340%

    No Known Activations