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. 5-RES-JB
    6. 17842
    Prev
    Next
    INDEX
    Explanations

    terms related to performance, capability, and potential in sports and related fields

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to sports player performance and potential

    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
     UNESCO
    -0.78
     Funding
    -0.73
     Federation
    -0.71
     Governments
    -0.70
    grave
    -0.68
     Administ
    -0.68
     ®
    -0.68
     Doctor
    -0.67
     Mahjong
    -0.66
     Editors
    -0.65
    POSITIVE LOGITS
     offensively
    1.21
     defensively
    1.03
     athleticism
    1.01
     signings
    1.00
     linem
    0.99
     undrafted
    0.98
     rookie
    0.96
     positional
    0.93
     backfield
    0.91
     linebacker
    0.90
    Activations Density 0.303%

    No Known Activations