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. 17733
    Prev
    Next
    INDEX
    Explanations

    references to sports events, particularly football games

    oai_token-act-pair · gpt-3.5-turbo

    references to various games, specifically sports games

    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
    aft
    -0.89
    asma
    -0.78
     manif
    -0.69
    rift
    -0.67
    xon
    -0.66
    doms
    -0.66
    ogle
    -0.66
    anol
    -0.66
     fert
    -0.65
     manifold
    -0.63
    POSITIVE LOGITS
     celebration
    0.83
    Day
    0.83
     festivities
    0.79
    aturday
    0.78
     kickoff
    0.78
     Stadium
    0.77
     Skydragon
    0.75
     Tues
    0.74
     Day
    0.74
     curfew
    0.74
    Activations Density 0.063%

    No Known Activations