© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 24279
    Prev
    Next
    INDEX
    Explanations

    mentions of X-ray technology

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of rays, particularly X-ray and gamma-ray

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abulary
    -0.72
    ifully
    -0.71
    uador
    -0.70
    ickers
    -0.70
    ãĤ¢ãĥ«
    -0.69
    itaire
    -0.67
    iability
    -0.67
     Mens
    -0.67
    icker
    -0.66
    HT
    -0.66
    POSITIVE LOGITS
    stals
    0.95
    von
    0.89
    mond
    0.85
    nor
    0.84
    oning
    0.83
    leigh
    0.81
    stal
    0.77
    ed
    0.77
     absor
    0.74
    sis
    0.73
    Activations Density 0.031%

    No Known Activations