© 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. 22695
    Prev
    Next
    INDEX
    Explanations

    words related to dietary restrictions and medical conditions, particularly concerning gluten and dairy

    oai_token-act-pair · gpt-3.5-turbo

    negative health-related terms or conditions

    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
     heights
    -0.87
     succession
    -0.80
     patience
    -0.79
     clocks
    -0.78
     redund
    -0.78
     square
    -0.75
     step
    -0.73
     execut
    -0.71
     salaries
    -0.70
     twenties
    -0.70
    POSITIVE LOGITS
    related
    1.76
    induced
    1.74
    containing
    1.67
    resistant
    1.66
    based
    1.66
    derived
    1.63
    free
    1.63
    associated
    1.62
    laden
    1.60
    specific
    1.57
    Activations Density 0.065%

    No Known Activations