© 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. 3-RES-JB
    11. 16744
    Prev
    Next
    INDEX
    Explanations

    medical conditions related to the brain and memory, specifically dementia and coma

    oai_token-act-pair · gpt-3.5-turbo

    terms related to life-threatening medical conditions and cognitive decline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andum
    -0.80
    tons
    -0.80
    ĥ
    -0.79
    Ĺ
    -0.79
    Ģ
    -0.77
    ī
    -0.76
    ĩ
    -0.76
    anooga
    -0.75
    Ĵ
    -0.71
    aire
    -0.71
    POSITIVE LOGITS
     coma
    0.93
    wcs
    0.84
     dementia
    0.80
     sickness
    0.75
     suff
    0.73
     versa
    0.73
    formation
    0.72
     ward
    0.71
    oooooooooooooooo
    0.71
     continuum
    0.71
    Activations Density 0.014%

    No Known Activations