© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 21470
    Prev
    Next
    INDEX
    Explanations

    references to sports coaches, especially expressing gratitude or acknowledgment

    oai_token-act-pair · gpt-3.5-turbo

    mentions of coaches in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    doms
    -0.76
     subjects
    -0.67
     revolt
    -0.67
     âĨij
    -0.65
     gathering
    -0.65
     shadow
    -0.63
     yuan
    -0.63
     mash
    -0.61
     fil
    -0.61
     relative
    -0.60
    POSITIVE LOGITS
     Coach
    3.78
    Coach
    3.25
     coach
    1.86
     coaches
    1.68
     coaching
    1.36
     Instructor
    1.29
     coached
    1.25
     Teacher
    1.22
     Manager
    1.20
     Coordinator
    1.20
    Activations Density 0.017%

    No Known Activations