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. 9-RES-JB
    6. 6460
    Prev
    Next
    INDEX
    Explanations

    descriptions of actions related to a sports event

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports events and game dynamics

    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
     contracting
    -0.80
    reprene
    -0.74
     leases
    -0.73
     Founder
    -0.73
     founding
    -0.73
     administr
    -0.72
    enegger
    -0.71
     unemploy
    -0.71
     vocational
    -0.71
     hires
    -0.71
    POSITIVE LOGITS
     replay
    1.32
     scoreboard
    1.21
     referee
    1.15
     halftime
    1.15
     score
    1.02
     spectators
    0.99
     cheers
    0.99
    Score
    0.97
     scorer
    0.96
     rematch
    0.95
    Activations Density 0.600%

    No Known Activations