Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11755
    Prev
    Next
    INDEX
    Explanations

    information related to eSports tournaments and player performances

    oai_token-act-pair · gpt-3.5-turbo

    references to competitive gaming events and their participants

    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
     Martha
    -0.90
     Hubbard
    -0.89
    ARDIS
    -0.88
     Dorothy
    -0.87
    Enlarge
    -0.85
     Dickens
    -0.83
     Manit
    -0.82
    gerald
    -0.80
    terson
    -0.80
    baugh
    -0.80
    POSITIVE LOGITS
     Fnatic
    1.70
     Dota
    1.48
     Esports
    1.42
     MLG
    1.42
     eSports
    1.41
     esports
    1.34
     ESL
    1.33
     StarCraft
    1.28
     Protoss
    1.24
     Starcraft
    1.23
    Activations Density 0.511%

    No Known Activations