© 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. 11-RES-JB
    11. 7618
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and treatments, especially those related to nerves and surgical procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical conditions and anatomical features

    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
    KEN
    -0.71
    LESS
    -0.64
    EStreamFrame
    -0.63
    EGIN
    -0.62
     Logged
    -0.62
    Dash
    -0.61
     Koen
    -0.60
    Sand
    -0.60
    Sah
    -0.60
    Prime
    -0.59
    POSITIVE LOGITS
    osis
    1.29
    iasis
    1.24
    rosis
    1.11
    ically
    1.09
    heric
    1.07
    otic
    1.06
    ics
    1.03
    itic
    1.03
    istics
    1.03
    istic
    1.02
    Activations Density 0.144%

    No Known Activations