© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 2660
    Prev
    Next
    INDEX
    Explanations

    words related to the Super Bowl

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Super Bowl

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     authorised
    -0.71
     regener
    -0.68
    д
    -0.63
     metab
    -0.63
     creep
    -0.63
    REP
    -0.62
     freel
    -0.61
     medic
    -0.61
    ev
    -0.61
     ren
    -0.60
    POSITIVE LOGITS
     Bowl
    4.26
    bowl
    2.72
     bowl
    1.98
     bowls
    1.96
     Cups
    1.31
     Football
    1.21
     Bow
    1.17
     Cup
    1.14
     Dome
    1.12
     Stadium
    1.08
    Activations Density 0.013%

    No Known Activations