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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19006
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams and competitions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to competitive group rankings and qualifications in esports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eteria
    -0.81
    trak
    -0.79
     Utt
    -0.73
    î
    -0.72
    DonaldTrump
    -0.72
    OUP
    -0.71
    thritis
    -0.70
    gerald
    -0.70
    aukee
    -0.70
    awaru
    -0.69
    POSITIVE LOGITS
     Dota
    1.35
     Starcraft
    1.22
     StarCraft
    1.21
     Zerg
    1.20
     eSports
    1.18
     Protoss
    1.11
     Fnatic
    1.10
     Esports
    1.08
     esports
    1.06
     tournament
    1.05
    Activations Density 0.384%

    No Known Activations