© 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. 4-RES-JB
    11. 15233
    Prev
    Next
    INDEX
    Explanations

    medical terms related to diagnosis

    oai_token-act-pair · gpt-3.5-turbo

    terms related to diagnostic criteria and assessments in mental health

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

    No Comments

    Negative Logits
    yss
    -0.85
    pload
    -0.81
     leisure
    -0.71
    sol
    -0.71
    hire
    -0.70
    asin
    -0.68
    uble
    -0.67
     reserve
    -0.66
    orld
    -0.66
    shi
    -0.65
    POSITIVE LOGITS
    ostics
    1.31
    ostic
    1.20
     Diagn
    1.01
     diagnoses
    0.99
     diagnosis
    0.93
    abetes
    0.83
    ptoms
    0.82
    agn
    0.81
     diagn
    0.81
    omatic
    0.78
    Activations Density 0.011%

    No Known Activations