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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 0-RES-JB
    6. 3279
    Prev
    Next
    INDEX
    Explanations

    the superlatives, particularly the word "Best."

    oai_token-act-pair · gpt-3.5-turbo

    the word "Best" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URI
    -0.68
    nir
    -0.66
     balloon
    -0.62
     colon
    -0.62
     prolifer
    -0.62
    sectional
    -0.61
     iron
    -0.61
    flies
    -0.61
    verse
    -0.60
    wolf
    -0.60
    POSITIVE LOGITS
     Best
    3.48
    Best
    2.67
     BEST
    2.15
    best
    2.15
     Worst
    2.02
     best
    1.90
     Favorite
    1.46
     Greatest
    1.39
    worst
    1.32
     Better
    1.28
    Activations Density 0.008%

    No Known Activations