© 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. 8-RES-JB
    11. 18632
    Prev
    Next
    INDEX
    Explanations

    references to sports games

    oai_token-act-pair · gpt-3.5-turbo

    references to the number of games in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yg
    -0.68
     politic
    -0.68
    uras
    -0.66
    200000
    -0.65
    ges
    -0.64
    xon
    -0.62
    sonian
    -0.62
    something
    -0.59
     Babel
    -0.59
    icators
    -0.58
    POSITIVE LOGITS
     played
    0.86
    manship
    0.85
     Played
    0.83
     opener
    0.80
     unbeaten
    0.78
    keepers
    0.77
    play
    0.73
     MVP
    0.73
    ulative
    0.72
    PLAY
    0.70
    Activations Density 0.047%

    No Known Activations