© 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. 7-RES-JB
    11. 13351
    Prev
    Next
    INDEX
    Explanations

    phrases related to competitive sports

    oai_token-act-pair · gpt-3.5-turbo

    references to competitive gaming and esports events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Martha
    -0.84
     Hubbard
    -0.84
    intendent
    -0.83
     Dickens
    -0.79
     Dorothy
    -0.79
     Eisenhower
    -0.79
    BOOK
    -0.78
     Hitchcock
    -0.76
     photoc
    -0.75
    Attorney
    -0.74
    POSITIVE LOGITS
     eSports
    1.36
     Esports
    1.30
     Fnatic
    1.28
     Dota
    1.25
     Protoss
    1.21
     Zerg
    1.17
     Starcraft
    1.10
     StarCraft
    1.10
     esports
    1.07
     Gaming
    1.03
    Activations Density 0.502%

    No Known Activations