© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20475
    Prev
    Next
    INDEX
    Explanations

    medical terms related to various conditions and disorders, particularly focusing on terms related to the nervous system and musculoskeletal system

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical conditions and disabilities

    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
    steen
    -0.78
    Reviewer
    -0.77
    LESS
    -0.73
    points
    -0.70
    assian
    -0.66
    Enlarge
    -0.65
     Foss
    -0.64
     Appl
    -0.63
    eele
    -0.62
     points
    -0.62
    POSITIVE LOGITS
    emic
    1.03
    emia
    0.94
    algia
    0.92
    otics
    0.90
    rosis
    0.88
    ic
    0.87
     disorders
    0.87
    ics
    0.83
    osis
    0.82
    activity
    0.81
    Activations Density 0.085%

    No Known Activations