© 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. 13880
    Prev
    Next
    INDEX
    Explanations

    phrases related to electronic commerce or emails

    oai_token-act-pair · gpt-3.5-turbo

    references to electronic communications, particularly related to e-books

    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
     railing
    -0.71
     Showdown
    -0.63
     Anthem
    -0.63
     Operator
    -0.61
     sway
    -0.59
     Painter
    -0.59
     mine
    -0.59
     objectively
    -0.59
     vocals
    -0.59
     reproduction
    -0.59
    POSITIVE LOGITS
    tymology
    1.49
    ternally
    1.32
    agles
    1.32
    ugen
    1.31
    arthed
    1.29
    thereal
    1.25
    thereum
    1.24
    commerce
    1.22
    gypt
    1.22
    Commerce
    1.21
    Activations Density 0.027%

    No Known Activations