© 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. 20334
    Prev
    Next
    INDEX
    Explanations

    terms related to medical specialties and scientific fields

    oai_token-act-pair · gpt-3.5-turbo
    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
     Doe
    -0.79
     unaccompanied
    -0.74
     lockout
    -0.74
     chained
    -0.73
     Bravo
    -0.73
     slee
    -0.68
     ransom
    -0.67
     defer
    -0.67
     discounts
    -0.67
     rush
    -0.66
    POSITIVE LOGITS
    ology
    1.67
    ologists
    1.57
    ologist
    1.54
    iology
    1.47
    etics
    1.43
    ological
    1.41
     sciences
    1.40
    science
    1.40
    odynamics
    1.38
    rolog
    1.36
    Activations Density 0.171%

    No Known Activations