© 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. 11-RES-JB
    11. 10262
    Prev
    Next
    INDEX
    Explanations

    phrases related to accidents and incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to accidents and their implications

    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
    Tea
    -0.90
    ormons
    -0.85
    á¸
    -0.79
    apest
    -0.76
    galitarian
    -0.75
    Hung
    -0.75
    ħĭ
    -0.75
    reen
    -0.74
     Emin
    -0.73
    iberal
    -0.72
    POSITIVE LOGITS
     accidents
    1.83
     accident
    1.73
     fatalities
    1.71
     crashes
    1.71
     crash
    1.66
     injuries
    1.58
     collisions
    1.49
     injury
    1.46
     Crash
    1.46
    Crash
    1.45
    Activations Density 0.550%

    No Known Activations