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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 18886
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Reynolds"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Reynolds" in various contexts, particularly related to sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ça
    -0.72
    tered
    -0.69
    celona
    -0.66
    ãĥ³
    -0.66
    ahi
    -0.65
     Soviet
    -0.65
     Iranian
    -0.63
     Athens
    -0.61
    ×
    -0.61
     Finnish
    -0.61
    POSITIVE LOGITS
     Reynolds
    1.31
     rall
    0.77
     kernels
    0.76
     Christensen
    0.75
    nor
    0.75
    enegger
    0.74
     Shooter
    0.73
    quist
    0.73
    phrine
    0.72
    cliffe
    0.71
    Activations Density 0.004%

    No Known Activations