© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 7478
    Prev
    Next
    INDEX
    Explanations

    medical conditions or acute events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to acute medical conditions and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ships
    -0.75
    wagen
    -0.72
    optional
    -0.68
    */(
    -0.66
     Guides
    -0.66
    advertisement
    -0.65
     darn
    -0.65
    vous
    -0.65
    tz
    -0.64
    =-=-=-=-=-=-=-=-
    -0.64
    POSITIVE LOGITS
     acute
    0.98
    entimes
    0.85
     eleph
    0.77
     poisoning
    0.75
     coronary
    0.74
     exacerb
    0.73
     sensitivity
    0.71
     pent
    0.71
    omatic
    0.71
     distress
    0.70
    Activations Density 0.006%

    No Known Activations