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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 4865
    Prev
    Next
    INDEX
    Explanations

    words related to esports

    oai_token-act-pair · gpt-3.5-turbo

    references to esports and specific esports titles or events

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

    No Comments

    Negative Logits
     Dull
    -0.78
     Hubbard
    -0.66
    ings
    -0.65
     Bord
    -0.65
    itud
    -0.64
    ston
    -0.64
     Laf
    -0.64
    bery
    -0.64
    drawn
    -0.64
     Shirley
    -0.64
    POSITIVE LOGITS
     esports
    1.01
     Esports
    0.89
     eSports
    0.88
    soc
    0.83
    LCS
    0.80
    ournaments
    0.78
     betting
    0.77
    pires
    0.76
    ORTS
    0.76
     Dota
    0.75
    Activations Density 0.020%

    No Known Activations