© 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. 0-RES-JB
    11. 20009
    Prev
    Next
    INDEX
    Explanations

    words related to hospitals or medical facilities

    oai_token-act-pair · gpt-3.5-turbo

    references to hospitals and health-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     paradox
    -0.76
     Hamm
    -0.74
     shack
    -0.74
     polyg
    -0.72
    hang
    -0.72
    gard
    -0.71
     Gins
    -0.70
     Graph
    -0.70
    baum
    -0.69
     Rhodes
    -0.68
    POSITIVE LOGITS
    itals
    1.99
    lly
    1.98
     Sharks
    1.64
    ¢
    1.52
    ppa
    1.40
     Thornton
    1.31
    fc
    1.28
    apixel
    1.23
    iuses
    1.18
    uine
    1.13
    Activations Density 0.037%

    No Known Activations