© 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. 8-RES-JB
    11. 16686
    Prev
    Next
    INDEX
    Explanations

    words related to heart health and cardiovascular conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to heart and cardiac health issues

    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
    lems
    -0.78
    "]=>
    -0.75
     Tradable
    -0.72
     Manziel
    -0.69
     Username
    -0.69
    inational
    -0.69
     Klingon
    -0.69
     Etsy
    -0.69
    HOU
    -0.68
    enance
    -0.67
    POSITIVE LOGITS
    iovascular
    1.17
     artery
    1.06
    ocard
    0.93
     disease
    0.92
     arteries
    0.88
     valves
    0.87
    beat
    0.84
     muscle
    0.84
     medication
    0.83
     abnormalities
    0.82
    Activations Density 0.041%

    No Known Activations