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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-RES-JB
    6. 15233
    Prev
    Next
    INDEX
    Explanations

    mentions of sports players and their achievements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to individual players and their performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    conom
    -0.91
    ptoms
    -0.86
    sth
    -0.86
    skirts
    -0.80
    netflix
    -0.80
    utterstock
    -0.78
    agate
    -0.78
    ::::::::
    -0.78
    issions
    -0.78
    displayText
    -0.77
    POSITIVE LOGITS
     player
    1.76
     guy
    1.41
     hitter
    1.39
     pitcher
    1.36
     athlete
    1.31
     lineman
    1.29
     defenseman
    1.28
     goaltender
    1.28
     defender
    1.27
     outfielder
    1.27
    Activations Density 0.286%

    No Known Activations