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. 8-RES-JB
    6. 21282
    Prev
    Next
    INDEX
    Explanations

    phrases related to soccer play-by-play commentary

    oai_token-act-pair · gpt-3.5-turbo

    sports-related actions and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FY
    -0.71
     Canaver
    -0.68
    CRIP
    -0.67
     iter
    -0.67
     perks
    -0.67
     investigations
    -0.64
     proofs
    -0.63
     pand
    -0.62
     Scient
    -0.62
     certs
    -0.62
    POSITIVE LOGITS
     goalkeeper
    0.98
     teammate
    0.94
     midfield
    0.94
     scorer
    0.86
     basket
    0.84
     outfield
    0.83
     fullback
    0.81
     rim
    0.81
     referee
    0.81
     contested
    0.78
    Activations Density 0.191%

    No Known Activations