© 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. 8-RES-JB
    11. 24297
    Prev
    Next
    INDEX
    Explanations

    specific references to players, readers, viewers, and users in a gaming or interactive setting

    oai_token-act-pair · gpt-3.5-turbo

    references to players and viewers in the context of gaming experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hots
    -0.77
    etting
    -0.75
    arus
    -0.74
    chool
    -0.73
    uca
    -0.73
    ippi
    -0.71
    equality
    -0.70
    poons
    -0.70
    hell
    -0.70
     Matter
    -0.70
    POSITIVE LOGITS
    's
    0.98
    ÃŃs
    0.87
     chooses
    0.86
    liest
    0.81
     himself
    0.80
     selects
    0.78
     assumes
    0.76
     knows
    0.76
    osphere
    0.75
     perce
    0.74
    Activations Density 0.225%

    No Known Activations