© 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. 21267
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical treatments and clinical trials

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to medical treatments and therapies

    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
    Export
    -0.74
    wn
    -0.73
    reve
    -0.72
    Dick
    -0.72
    begin
    -0.70
    local
    -0.70
    bour
    -0.69
    prints
    -0.67
    earth
    -0.67
    jp
    -0.65
    POSITIVE LOGITS
     regimen
    1.12
     treatments
    1.06
     therapies
    1.04
     therapy
    1.01
     treatment
    0.98
     therape
    0.95
     Treatment
    0.93
     medication
    0.92
     medications
    0.91
    treatment
    0.90
    Activations Density 0.026%

    No Known Activations