© 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. 11-RES-JB
    11. 6254
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions, treatments, and statistics related to people

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and groups in the context of health and medical conditions

    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
    tainment
    -1.07
    rawdownloadcloneembedreportprint
    -0.74
    HCR
    -0.67
    ãĥķãĤ©
    -0.65
    ãģĨ
    -0.64
    apixel
    -0.64
    ãĥ¥
    -0.62
    aughs
    -0.62
    prises
    -0.61
    æĪ¦
    -0.61
    POSITIVE LOGITS
     diagnosed
    1.29
     undergoing
    1.20
     aged
    1.19
     whose
    1.15
     born
    1.15
     who
    1.14
     afflicted
    1.11
     experiencing
    1.07
     suffering
    1.06
     with
    1.03
    Activations Density 0.220%

    No Known Activations