© 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. 4-RES-JB
    11. 17307
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "games" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of games played in sports contexts

    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
     politic
    -0.84
    yg
    -0.78
    icultural
    -0.77
    sie
    -0.71
    eous
    -0.70
    eton
    -0.69
    ges
    -0.68
    ract
    -0.65
    200000
    -0.63
    asin
    -0.63
    POSITIVE LOGITS
     Played
    0.85
    士
    0.80
    poons
    0.79
     played
    0.78
     expectancy
    0.78
     Ago
    0.75
     games
    0.74
     opener
    0.74
     apiece
    0.73
    day
    0.73
    Activations Density 0.032%

    No Known Activations