© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7834
    Prev
    Next
    INDEX
    Explanations

    descriptions of vehicular accidents

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to vehicle collisions and accidents

    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
     persuasion
    -0.69
    bern
    -0.68
     Username
    -0.67
    tz
    -0.65
     lia
    -0.62
     meetings
    -0.62
     deleg
    -0.62
    Ur
    -0.62
    assadors
    -0.62
    Pand
    -0.61
    POSITIVE LOGITS
     debris
    1.13
     collision
    1.09
     crash
    1.07
     injuring
    1.05
     windshield
    1.03
     injure
    1.03
     crashes
    1.02
     collided
    0.98
     crashed
    0.94
     crashing
    0.88
    Activations Density 0.487%

    No Known Activations