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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-RES-JB
    6. 18750
    Prev
    Next
    INDEX
    Explanations

    specific mentions of "Super Bowl" events

    oai_token-act-pair · gpt-3.5-turbo

    references to the Super Bowl and its various iterations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atem
    -0.81
    auga
    -0.75
    Downloadha
    -0.74
    uph
    -0.73
    abet
    -0.71
    ogly
    -0.71
    apons
    -0.71
    govtrack
    -0.70
    ifles
    -0.70
    ements
    -0.70
    POSITIVE LOGITS
     XL
    1.02
     halftime
    1.01
     XXX
    0.98
     LI
    0.97
     Winners
    0.89
     Finals
    0.89
     Bowl
    0.86
     Playoff
    0.86
     Playoffs
    0.84
     Winning
    0.83
    Activations Density 0.036%

    No Known Activations