© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 7080
    Prev
    Next
    INDEX
    Explanations

    medical terms and research-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to medical assessments and statistical health metrics

    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
    UTF
    -0.78
     Stronghold
    -0.78
    Artist
    -0.77
    Untitled
    -0.76
     tiles
    -0.74
    Catalog
    -0.74
    FTWARE
    -0.73
    ãĥķãĤ©
    -0.72
     Luffy
    -0.71
     Strongh
    -0.71
    POSITIVE LOGITS
     clinical
    1.34
     cardiovascular
    1.33
     medication
    1.31
     psychiatric
    1.30
     clinically
    1.28
     pediatric
    1.23
     diagnosis
    1.23
     patients
    1.22
     diabetes
    1.20
     coronary
    1.20
    Activations Density 0.764%

    No Known Activations