© 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. 9-RES-JB
    11. 2829
    Prev
    Next
    INDEX
    Explanations

    medical conditions, technical terms, and various other specialized terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to medical or scientific terms and peer-reviewed concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ´ãĤ¡
    -0.73
    appropriately
    -0.67
    bably
    -0.65
    ivably
    -0.64
    perate
    -0.63
    liest
    -0.61
    putable
    -0.59
    uably
    -0.59
     Brav
    -0.59
    bare
    -0.59
    POSITIVE LOGITS
    isations
    0.68
    ities
    0.68
    unia
    0.67
    ebted
    0.63
    earances
    0.63
    acters
    0.63
    nces
    0.62
    anism
    0.62
    hemy
    0.61
    anse
    0.61
    Activations Density 0.743%

    No Known Activations