© 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. 3-RES-JB
    11. 12492
    Prev
    Next
    INDEX
    Explanations

    terms related to clinical settings, such as clinical practice, clinical psychologist, clinical trials, and clinical research

    oai_token-act-pair · gpt-3.5-turbo

    mentions of clinical practices or professionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĺ
    -0.81
    uble
    -0.75
    ERC
    -0.73
    Lago
    -0.69
     Hood
    -0.69
     Kinnikuman
    -0.68
    Dick
    -0.68
    leted
    -0.65
    lda
    -0.65
    estamp
    -0.65
    POSITIVE LOGITS
     trials
    0.99
     practition
    0.96
     diagnoses
    0.90
     practitioners
    0.89
     evaluations
    0.87
     clinical
    0.86
     diagnosis
    0.83
     treatments
    0.81
     Trials
    0.80
     manifestations
    0.80
    Activations Density 0.012%

    No Known Activations