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. 8-RES-JB
    6. 4667
    Prev
    Next
    INDEX
    Explanations

    names of sports coaches

    oai_token-act-pair · gpt-3.5-turbo

    names and titles related to coaches and managers in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WOM
    -0.81
    enezuel
    -0.76
    â̦â̦â̦â̦â̦â̦â̦â̦
    -0.75
     boobs
    -0.74
     heroine
    -0.74
    schild
    -0.73
     vulner
    -0.71
     Shutterstock
    -0.71
    gettable
    -0.69
     Intercept
    -0.68
    POSITIVE LOGITS
     coach
    0.97
     Coach
    0.91
     coaching
    0.86
    management
    0.85
     coaches
    0.84
     Brewer
    0.83
     coached
    0.82
     Rams
    0.82
     Management
    0.82
     Vog
    0.82
    Activations Density 0.169%

    No Known Activations