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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8702
    Prev
    Next
    INDEX
    Explanations

    mentions of football teams and their performance, particularly focusing on defense

    oai_token-act-pair · gpt-3.5-turbo
    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
    reprene
    -0.72
    Britain
    -0.71
    dit
    -0.69
     Tinder
    -0.69
    AFTA
    -0.69
    Virgin
    -0.69
     Greenpeace
    -0.68
     refere
    -0.68
    Pic
    -0.68
    untary
    -0.66
    POSITIVE LOGITS
     lineback
    1.28
     roster
    1.27
     defensively
    1.20
     offensively
    1.19
     rookies
    1.17
     rosters
    1.17
     inept
    1.16
     firepower
    1.12
     offense
    1.11
     bullpen
    1.11
    Activations Density 0.383%

    No Known Activations