© 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 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. 0-RES-JB
    11. 9671
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "gamer" in the context of various articles or discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to gaming and gamers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ca
    -0.79
     Silva
    -0.77
     Sic
    -0.74
     Vend
    -0.72
     Klaus
    -0.67
     Fei
    -0.66
     Pros
    -0.66
     Michaels
    -0.66
     Hope
    -0.66
    Ãĥ
    -0.65
    POSITIVE LOGITS
    gamer
    3.62
    gam
    1.52
    amus
    1.36
     gamer
    1.23
    reader
    1.19
     Kang
    1.15
     Yog
    1.04
    Gamer
    0.99
    plays
    0.98
    jew
    0.96
    Activations Density 0.045%

    No Known Activations