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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 12990
    Prev
    Next
    INDEX
    Explanations

    mentions related to a specific entity or team, "FaZe."

    oai_token-act-pair · gpt-3.5-turbo

    teams and players within competitive gaming contexts

    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
    uphem
    -0.74
    psc
    -0.70
    artisan
    -0.69
    cloth
    -0.67
    comings
    -0.66
    tons
    -0.66
    \/\/
    -0.65
     Hoover
    -0.64
     voucher
    -0.64
    agna
    -0.64
    POSITIVE LOGITS
     eSports
    1.08
     Esports
    1.06
     Gaming
    0.97
     Wolves
    0.92
    XT
    0.88
    YP
    0.80
     Racing
    0.80
     Fnatic
    0.79
    Zen
    0.79
     teammate
    0.75
    Activations Density 0.130%

    No Known Activations