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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9994
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific American football team, the Washington Redskins

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Redskins football team and related context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    judicial
    -0.81
    ote
    -0.77
    arching
    -0.76
    olean
    -0.75
    ör
    -0.74
    lder
    -0.74
    ered
    -0.74
    sb
    -0.73
    ement
    -0.71
    oshi
    -0.70
    POSITIVE LOGITS
     Redskins
    0.96
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.91
     Nationals
    0.90
     Capitals
    0.87
    istani
    0.80
    daq
    0.79
     Express
    0.78
     Chiefs
    0.75
     Cousins
    0.70
    士
    0.70
    Activations Density 0.026%

    No Known Activations