© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11430
    Prev
    Next
    INDEX
    Explanations

    named entities in sports

    oai_token-act-pair · gpt-3.5-turbo

    mentions of esports teams and matches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     typew
    -0.93
     Dickens
    -0.92
    Enlarge
    -0.92
    sonian
    -0.89
     broch
    -0.83
     Martha
    -0.83
     Hubbard
    -0.82
    baugh
    -0.81
     grocer
    -0.81
    resa
    -0.79
    POSITIVE LOGITS
     Fnatic
    1.51
     eSports
    1.34
     Esports
    1.32
     Dota
    1.29
     Protoss
    1.27
     PvP
    1.27
     Zerg
    1.25
     StarCraft
    1.20
     tournament
    1.20
     tournaments
    1.14
    Activations Density 0.739%

    No Known Activations