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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 19306
    Prev
    Next
    INDEX
    Explanations

    names of wrestlers and terms related to wrestling, such as titles, submissions, and championships

    oai_token-act-pair · gpt-3.5-turbo

    references to professional wrestling events and terminology

    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
    Newsletter
    -0.86
     Gutenberg
    -0.80
     Helpful
    -0.80
    ername
    -0.78
     UNCLASSIFIED
    -0.73
    iterranean
    -0.72
    ulhu
    -0.72
    Reviewer
    -0.72
    ickr
    -0.71
     Bhar
    -0.70
    POSITIVE LOGITS
     rematch
    1.08
     bout
    0.92
     MMA
    0.92
     wrestlers
    0.92
     bouts
    0.91
     steroid
    0.91
     steroids
    0.91
     stopp
    0.88
     Showdown
    0.87
     fights
    0.85
    Activations Density 0.157%

    No Known Activations