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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 19308
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and player names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of player statistics and performances in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     photoc
    -0.73
     Google
    -0.72
     volunt
    -0.72
     feminism
    -0.71
     FOIA
    -0.71
     dialog
    -0.71
     treaties
    -0.70
     reprodu
    -0.70
     NGOs
    -0.70
     Ada
    -0.69
    POSITIVE LOGITS
    ï¸ı
    1.15
    season
    1.13
    league
    1.05
    team
    1.03
    League
    1.03
    ftime
    1.03
     preseason
    1.02
    NFL
    1.02
     playoff
    1.01
    finals
    1.00
    Activations Density 0.211%

    No Known Activations