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. 22092
    Prev
    Next
    INDEX
    Explanations

    sports-related terms like "coach" and specific names of coaches and managers

    oai_token-act-pair · gpt-3.5-turbo

    references to sports team management and coaching roles

    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
    MpServer
    -0.86
    EStreamFrame
    -0.82
    Gaza
    -0.78
    thodox
    -0.78
    wives
    -0.75
    tein
    -0.73
    ploy
    -0.73
    heid
    -0.71
    utterstock
    -0.70
    ratom
    -0.67
    POSITIVE LOGITS
     Steve
    1.02
     Ben
    1.00
     Bruce
    0.99
     Tim
    0.99
     Colin
    0.99
     Terry
    0.98
     Mark
    0.98
     Tony
    0.97
     Eddie
    0.97
     Justin
    0.97
    Activations Density 0.150%

    No Known Activations