© 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. 10-RES-JB
    11. 17303
    Prev
    Next
    INDEX
    Explanations

    medical symptoms and conditions

    oai_token-act-pair · gpt-3.5-turbo

    medical symptoms and their descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saf
    -0.90
    udeau
    -0.86
    tackle
    -0.82
    arenthood
    -0.77
     responsibly
    -0.75
     Industries
    -0.74
     Ethics
    -0.73
    esan
    -0.73
    avorite
    -0.73
    rules
    -0.73
    POSITIVE LOGITS
     nausea
    1.42
     vomiting
    1.38
     coughing
    1.36
     headaches
    1.36
     hallucinations
    1.31
     dizz
    1.26
     numb
    1.26
     headache
    1.26
     sensations
    1.25
     itching
    1.23
    Activations Density 0.252%

    No Known Activations