© 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. 9-RES-JB
    11. 11147
    Prev
    Next
    INDEX
    Explanations

    descriptions of vehicular accidents

    oai_token-act-pair · gpt-3.5-turbo

    incidents involving vehicle collisions and crashes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocations
    -0.74
    eln
    -0.73
     persuasion
    -0.72
    ËĪ
    -0.72
    assadors
    -0.71
     voicing
    -0.70
     lia
    -0.70
    IQ
    -0.68
    Ur
    -0.68
     appe
    -0.68
    POSITIVE LOGITS
     windshield
    1.10
     debris
    1.08
     parked
    0.97
     pedestrians
    0.95
     collision
    0.89
     wreckage
    0.88
     injuring
    0.87
     rocks
    0.86
     asphalt
    0.83
     fragments
    0.83
    Activations Density 0.283%

    No Known Activations