© 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. 10-RES-JB
    11. 16064
    Prev
    Next
    INDEX
    Explanations

    submissions or references to external sources

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Sub" and its variations, likely denoting submissions or sections in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agne
    -0.67
     laughter
    -0.65
     Muse
    -0.63
     wings
    -0.63
     pron
    -0.62
     fir
    -0.62
     sake
    -0.62
     wool
    -0.62
     fingerprint
    -0.62
    ATHER
    -0.62
    POSITIVE LOGITS
    sequent
    1.62
    sequently
    1.62
    stantial
    1.61
    mitted
    1.57
    scription
    1.47
    ordinate
    1.40
    stant
    1.39
    marine
    1.36
    missions
    1.32
    mitting
    1.31
    Activations Density 0.019%

    No Known Activations