© 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. 8-RES-JB
    6. 9864
    Prev
    Next
    INDEX
    Explanations

    words related to a specific medical condition or name 'Guill', which might be associated with Guillain-Barré syndrome or other Guill-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific medical conditions and their manifestations

    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
     pestic
    -0.68
     Treaty
    -0.67
     adolesc
    -0.65
    NetMessage
    -0.62
    dfx
    -0.60
     practices
    -0.60
    Ô
    -0.59
     resid
    -0.58
     agreements
    -0.58
     reversible
    -0.57
    POSITIVE LOGITS
    anamo
    1.05
    fecture
    0.83
    ierrez
    0.79
    antam
    0.78
    arent
    0.78
    yan
    0.74
    otine
    0.73
    uid
    0.72
    arest
    0.71
    wine
    0.70
    Activations Density 0.072%

    No Known Activations