© 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. 24096
    Prev
    Next
    INDEX
    Explanations

    sports-related information, particularly about player statistics and team dynamics

    oai_token-act-pair · gpt-3.5-turbo

    elements related to sports statistics and player performance

    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
    Hundreds
    -0.75
    Muslims
    -0.74
    democratic
    -0.73
    ictionary
    -0.72
    Woman
    -0.72
    opath
    -0.71
    verend
    -0.70
    Nazi
    -0.70
    nuclear
    -0.70
    Jewish
    -0.69
    POSITIVE LOGITS
     rookie
    1.26
     teammate
    1.17
     he
    1.14
     undrafted
    1.12
     coach
    1.10
     rookies
    1.09
     Rookie
    1.05
     scouts
    1.04
     Cousins
    1.04
     Defensive
    1.03
    Activations Density 0.250%

    No Known Activations