© 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. 11-RES-JB
    11. 22061
    Prev
    Next
    INDEX
    Explanations

    information related to awards and voting processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to votes and awards in sports contexts

    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
     crap
    -0.74
     scept
    -0.74
     panicked
    -0.73
     shit
    -0.72
     revolt
    -0.71
     cens
    -0.71
     horr
    -0.69
    toggle
    -0.69
     censored
    -0.69
     centrist
    -0.68
    POSITIVE LOGITS
    Coach
    1.39
    Football
    1.37
     Coach
    1.29
     coaching
    1.26
     Hockey
    1.23
     Basketball
    1.23
     USL
    1.22
    Players
    1.20
     coaches
    1.19
     Athletics
    1.19
    Activations Density 0.501%

    No Known Activations