© 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. 11272
    Prev
    Next
    INDEX
    Explanations

    words related to technology and events in recent history

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns related to technology, entertainment, and societal issues

    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
    ilk
    -0.87
    ensional
    -0.68
    ãĤĮ
    -0.66
    00200000
    -0.66
    ulz
    -0.65
    cgi
    -0.64
    alle
    -0.64
    ité
    -0.63
    reditary
    -0.62
    rez
    -0.62
    POSITIVE LOGITS
     imaginable
    1.13
     EVER
    1.03
     ever
    0.95
     besides
    0.80
     anywhere
    0.77
     conceivable
    0.76
     Ever
    0.74
     contender
    0.66
     accol
    0.65
     sighting
    0.64
    Activations Density 0.419%

    No Known Activations