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. 4224
    Prev
    Next
    INDEX
    Explanations

    phrases related to successful or dominant performance in sports

    oai_token-act-pair · gpt-3.5-turbo

    strong performance indicators in sports contexts

    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
     concess
    -0.72
     Lifetime
    -0.72
    Leaks
    -0.70
    OPLE
    -0.69
     confidentiality
    -0.69
    iannopoulos
    -0.67
    nih
    -0.66
    uphem
    -0.66
    Scient
    -0.66
     memos
    -0.62
    POSITIVE LOGITS
     offensively
    1.58
     defensively
    1.47
     territ
    1.12
     tonight
    1.08
     scoring
    1.04
     playoff
    1.03
     athlet
    1.02
     defending
    1.02
     heading
    1.00
     against
    1.00
    Activations Density 0.294%

    No Known Activations