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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 22305
    Prev
    Next
    INDEX
    Explanations

    words related to accidents and incidents

    oai_token-act-pair · gpt-3.5-turbo

    discussions around accidents and disasters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     offer
    -0.77
     proposal
    -0.76
     approach
    -0.76
     message
    -0.73
     site
    -0.73
     invitation
    -0.72
     piece
    -0.72
     dossier
    -0.71
     envelope
    -0.71
    gue
    -0.70
    POSITIVE LOGITS
     accidents
    2.61
     collisions
    2.07
     disasters
    2.06
     crashes
    1.89
     tragedies
    1.86
     earthquakes
    1.85
     emergencies
    1.82
     hurricanes
    1.78
     crises
    1.75
     scandals
    1.72
    Activations Density 0.056%

    No Known Activations