© 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. 2997
    Prev
    Next
    INDEX
    Explanations

    terms related to WWE matches and events

    oai_token-act-pair · gpt-3.5-turbo

    references to professional wrestling events and organizations, specifically WWE and WrestleMania

    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
    lasses
    -0.86
    yrinth
    -0.84
    pmwiki
    -0.74
    uries
    -0.70
    uckland
    -0.70
    ĺħ
    -0.69
    perse
    -0.68
    undai
    -0.67
    pard
    -0.67
    abet
    -0.67
    POSITIVE LOGITS
    Mania
    1.23
     Wrestle
    1.17
    restling
    1.16
     NXT
    1.10
     McMahon
    1.06
    mania
    1.03
     wrestlers
    1.02
     Wrestling
    0.98
     Wrest
    0.96
     wrestler
    0.95
    Activations Density 0.058%

    No Known Activations