Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15910
    Prev
    Next
    INDEX
    Explanations

    information related to driving and traffic accidents

    oai_token-act-pair · gpt-3.5-turbo

    actions related to driving and traffic incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.77
     psy
    -0.67
     organising
    -0.66
    ertain
    -0.66
     dressing
    -0.62
     Bahá
    -0.61
     exile
    -0.61
     cous
    -0.60
     weddings
    -0.60
     inoc
    -0.59
    POSITIVE LOGITS
     onto
    0.96
     parked
    0.96
     headlights
    0.93
     brakes
    0.92
     traffic
    0.90
     lanes
    0.86
     lane
    0.86
     brake
    0.86
     Interstate
    0.85
     driveway
    0.85
    Activations Density 0.174%

    No Known Activations