© 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. 13696
    Prev
    Next
    INDEX
    Explanations

    words related to sports, games, and competition

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to confidence and performance in sports

    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
     Citiz
    -0.68
    DATA
    -0.67
    obos
    -0.66
    bris
    -0.63
    sels
    -0.62
     horrors
    -0.59
    ãĥ©ãĥ³
    -0.58
     scant
    -0.57
    NAME
    -0.56
     bidder
    -0.55
    POSITIVE LOGITS
    .''
    1.35
    ."
    1.25
    laughs
    1.21
    .�
    1.14
    ,''
    1.09
    .
    1.08
     because
    1.06
    ,"
    1.03
    .'
    1.01
     [
    0.98
    Activations Density 0.420%

    No Known Activations