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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 9-RES-JB
    6. 22552
    Prev
    Next
    INDEX
    Explanations

    verbs related to sports performance and teamwork

    oai_token-act-pair · gpt-3.5-turbo

    positive evaluations of performance or skill in a sports context

    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
     PBS
    -0.66
     subscriptions
    -0.60
     Yelp
    -0.58
     Journals
    -0.58
    indust
    -0.58
     jurisd
    -0.57
     AOL
    -0.57
     NPR
    -0.57
     licensing
    -0.57
     Freem
    -0.56
    POSITIVE LOGITS
     defensively
    1.03
     offensively
    1.03
     midfield
    1.02
     clutch
    0.93
     teammate
    0.92
     teammates
    0.91
     scoring
    0.91
     defensive
    0.90
     defender
    0.88
     versatility
    0.87
    Activations Density 1.177%

    No Known Activations