© 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. 11482
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports positions and player abilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to player performance and attributes in sports, particularly in the context of football

    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
    Wan
    -0.76
    netflix
    -0.71
    laughs
    -0.69
     Carnival
    -0.68
    laws
    -0.67
     unpublished
    -0.67
     Journals
    -0.66
    Strange
    -0.66
     holidays
    -0.66
     Indra
    -0.64
    POSITIVE LOGITS
     defender
    1.27
     scorer
    1.27
     offensively
    1.25
     passer
    1.20
     hitter
    1.19
     blocker
    1.19
     rusher
    1.17
     offense
    1.15
     defensively
    1.12
     quarterback
    1.11
    Activations Density 0.232%

    No Known Activations