© 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. 11-RES-JB
    11. 15717
    Prev
    Next
    INDEX
    Explanations

    medical conditions or treatments

    oai_token-act-pair · gpt-3.5-turbo

    segments indicating medical conditions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     neighb
    -0.93
     aligned
    -0.85
    mble
    -0.84
     sket
    -0.83
     bounded
    -0.82
     materially
    -0.82
    ĪĴ
    -0.80
     occup
    -0.80
     patronage
    -0.80
     nomine
    -0.80
    POSITIVE LOGITS
     Symptoms
    1.76
    Doctors
    1.60
     Patients
    1.55
    Sym
    1.53
    Studies
    1.45
    Researchers
    1.42
     Diseases
    1.40
     Researchers
    1.38
     Diabetes
    1.38
     Doctors
    1.36
    Activations Density 0.349%

    No Known Activations