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. 4-RES-JB
    6. 23090
    Prev
    Next
    INDEX
    Explanations

    mentions of the Washington Redskins and their associated activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of the sports team "Redskins"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    judicial
    -0.79
    blow
    -0.78
    itia
    -0.71
    tered
    -0.71
    htaking
    -0.71
    block
    -0.70
    lder
    -0.70
    oshi
    -0.70
    ör
    -0.69
    redited
    -0.69
    POSITIVE LOGITS
     Redskins
    1.05
    istani
    0.96
    daq
    0.88
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.84
     Cousins
    0.83
    士
    0.74
    kies
    0.73
     Rapids
    0.71
     Express
    0.70
     Nationals
    0.69
    Activations Density 0.009%

    No Known Activations