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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 7557
    Prev
    Next
    INDEX
    Explanations

    references to the sports team "Washington Redskins"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Washington Redskins and related sports terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ishly
    -0.76
    robe
    -0.70
    elsen
    -0.69
    ework
    -0.67
    orate
    -0.67
    strap
    -0.66
    ement
    -0.65
    lder
    -0.64
    erence
    -0.62
    ---------------
    -0.62
    POSITIVE LOGITS
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.86
    icum
    0.84
    ules
    0.84
    abies
    0.82
    geon
    0.78
    ule
    0.78
    iculture
    0.74
    nesday
    0.74
    halla
    0.72
    istani
    0.72
    Activations Density 0.097%

    No Known Activations