© 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. 10-RES-JB
    11. 13737
    Prev
    Next
    INDEX
    Explanations

    mentions of specific sports positions and player names

    oai_token-act-pair · gpt-3.5-turbo

    names and positions of football players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ét
    -0.87
    Nintendo
    -0.86
    ÃŃa
    -0.80
     esports
    -0.79
     whisky
    -0.73
     Madrid
    -0.73
    wcsstore
    -0.71
     Paradox
    -0.70
     ATP
    -0.70
    rational
    -0.70
    POSITIVE LOGITS
    tackle
    1.54
     linebackers
    1.50
     linebacker
    1.47
     lineback
    1.42
     linemen
    1.38
     lineman
    1.33
     rusher
    1.29
     cornerback
    1.29
     tackles
    1.22
     sacks
    1.20
    Activations Density 0.495%

    No Known Activations