© 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. 814
    Prev
    Next
    INDEX
    Explanations

    scientific and medical terms related to diseases and conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various medical conditions and diseases

    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
     rooft
    -0.74
    livious
    -0.72
    endars
    -0.68
    bucks
    -0.65
    parency
    -0.63
     choir
    -0.63
     Vote
    -0.62
     Kislyak
    -0.62
     Values
    -0.62
     drafts
    -0.62
    POSITIVE LOGITS
     diagnosed
    1.39
     hereditary
    1.28
     caused
    1.23
     debilitating
    1.22
     reversible
    1.13
     autoimmune
    1.11
     contagious
    1.10
    diagn
    1.08
     fatal
    1.08
     disabling
    1.06
    Activations Density 0.173%

    No Known Activations