© 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. 2812
    Prev
    Next
    INDEX
    Explanations

    mentions of television shows and specific dates or events happening on the show

    oai_token-act-pair · gpt-3.5-turbo

    references to reality television events and characters

    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
     Stur
    -0.85
    ibraries
    -0.83
    rir
    -0.77
     Friedrich
    -0.76
     Erd
    -0.76
     Engels
    -0.74
    iegel
    -0.72
     Lenin
    -0.70
    Publisher
    -0.70
    Batman
    -0.70
    POSITIVE LOGITS
     contestant
    1.94
     contestants
    1.86
     Survivor
    1.60
    Surv
    1.43
     Immunity
    1.34
     Tribal
    1.32
     Contest
    1.22
     Prob
    1.17
     elim
    1.16
     pageant
    1.16
    Activations Density 0.157%

    No Known Activations