Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12459
    Prev
    Next
    INDEX
    Explanations

    phrases related to WWE and wrestling events

    oai_token-act-pair · gpt-3.5-turbo

    references to WWE and its events, specifically focusing on its wrestlers and championships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heid
    -0.86
    anwhile
    -0.85
    ouver
    -0.83
     MacArthur
    -0.80
    emort
    -0.79
     BART
    -0.77
    elong
    -0.77
    lasses
    -0.76
    uries
    -0.75
    perse
    -0.73
    POSITIVE LOGITS
    restling
    1.10
     NXT
    1.07
    Mania
    1.01
     Universe
    0.98
     Wrestle
    0.90
     wrestlers
    0.81
     Championship
    0.81
     WWE
    0.80
     Wrest
    0.79
     wrestling
    0.78
    Activations Density 0.024%

    No Known Activations