© 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. 1-RES-JB
    11. 954
    Prev
    Next
    INDEX
    Explanations

    terms related to Parkinson's disease and dopamine

    oai_token-act-pair · gpt-3.5-turbo

    references to Parkinson's disease and its related medical conditions

    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
    ILE
    -0.79
    ELF
    -0.78
    APE
    -0.78
    76561
    -0.75
     Bie
    -0.73
    EXP
    -0.73
    MET
    -0.71
    ÃįÃį
    -0.71
     SERV
    -0.71
    ISON
    -0.71
    POSITIVE LOGITS
     Parkinson
    0.96
    oshenko
    0.90
    inson
    0.89
    phrine
    0.85
     kidney
    0.82
    ricular
    0.82
    etsk
    0.80
    hurst
    0.75
    shire
    0.74
    bledon
    0.72
    Activations Density 0.005%

    No Known Activations