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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 6551
    Prev
    Next
    INDEX
    Explanations

    references to free agency in sports

    oai_token-act-pair · gpt-3.5-turbo

    references to agency in various contexts, particularly in the realm of sports

    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
    borough
    -0.74
    gran
    -0.73
    Hyper
    -0.69
     Haram
    -0.69
    iam
    -0.69
    nen
    -0.69
    ibo
    -0.68
     Hyper
    -0.66
    reme
    -0.66
     Barrier
    -0.65
    POSITIVE LOGITS
     signings
    0.93
     contracts
    0.84
     rosters
    0.82
     marketplace
    0.80
     Contracts
    0.74
     lottery
    0.74
    irting
    0.73
    Agent
    0.73
     acquisitions
    0.72
     auctions
    0.72
    Activations Density 0.013%

    No Known Activations