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. 4-RES-JB
    6. 3814
    Prev
    Next
    INDEX
    Explanations

    words related to transactions in sports, particularly free agency

    oai_token-act-pair · gpt-3.5-turbo

    references to "free agency" in sports contexts

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

    No Comments

    Negative Logits
    borough
    -0.75
    gran
    -0.75
    kai
    -0.74
    TPS
    -0.73
     Haram
    -0.72
     Gaw
    -0.68
    iam
    -0.67
     Scal
    -0.67
    vic
    -0.67
    na
    -0.66
    POSITIVE LOGITS
     signings
    0.91
     contracts
    0.85
     marketplace
    0.82
     rosters
    0.80
     workouts
    0.78
     pact
    0.77
     recruiting
    0.76
     lottery
    0.75
    inventoryQuantity
    0.74
     alternatives
    0.73
    Activations Density 0.008%

    No Known Activations