© 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. 1252
    Prev
    Next
    INDEX
    Explanations

    phrases related to image captions, photography, and credits

    oai_token-act-pair · gpt-3.5-turbo

    references to media sources and visual content

    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
     Paran
    -0.91
     behav
    -0.79
     exting
    -0.78
     metic
    -0.74
     Chev
    -0.70
     warr
    -0.68
    ãĤ¡
    -0.67
    Þ
    -0.66
     Ples
    -0.64
     bis
    -0.62
    POSITIVE LOGITS
    ini
    0.80
     Cosponsors
    0.73
    ina
    0.67
    %]
    0.65
     [|
    0.65
    000
    0.64
    ¿
    0.64
     [[
    0.64
     []
    0.64
    ));
    0.63
    Activations Density 0.201%

    No Known Activations