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. 15084
    Prev
    Next
    INDEX
    Explanations

    mentions of sports contracts and player signings

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

    phrases related to player contracts and signings in sports

    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
    Discuss
    -0.70
     sinks
    -0.70
    govtrack
    -0.69
    falls
    -0.67
     Indra
    -0.65
    TPPStreamerBot
    -0.64
    roman
    -0.64
    enges
    -0.64
     caut
    -0.62
    rencies
    -0.61
    POSITIVE LOGITS
     extension
    1.02
     contract
    1.00
     deal
    1.00
     lucrative
    0.92
     pact
    0.89
     qualifying
    0.85
     restruct
    0.80
     max
    0.80
     extensions
    0.78
    /$
    0.77
    Activations Density 0.080%

    No Known Activations