© 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. 23479
    Prev
    Next
    INDEX
    Explanations

    physical symptoms and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    medical symptoms and conditions related to various 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
    saf
    -0.80
     Tycoon
    -0.79
    rolet
    -0.75
     bidder
    -0.74
    tarians
    -0.73
    ãĤ¨ãĥ«
    -0.72
    rules
    -0.70
    winner
    -0.70
    Rules
    -0.70
    esan
    -0.69
    POSITIVE LOGITS
     symptoms
    1.43
     Symptoms
    1.22
     nausea
    1.21
     vomiting
    1.20
     headaches
    1.19
     symptom
    1.18
     sensations
    1.18
     sensation
    1.17
     headache
    1.15
    ptoms
    1.14
    Activations Density 0.457%

    No Known Activations