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. 2-RES-JB
    6. 65
    Prev
    Next
    INDEX
    Explanations

    words related to praise and congratulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing congratulations or praise

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

    words of congratulation, especially the word "Congratulations"

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subsistence
    -0.67
     zoning
    -0.67
     dangerously
    -0.66
     densely
    -0.66
     medic
    -0.63
    wild
    -0.62
    ved
    -0.62
    const
    -0.62
     habitable
    -0.62
     Wonderland
    -0.61
    POSITIVE LOGITS
    Congratulations
    1.47
     Congratulations
    1.37
     congratulations
    1.28
     congr
    1.19
    ratulations
    1.05
    rats
    1.00
     congratulate
    0.88
    issance
    0.87
    DragonMagazine
    0.84
    acebook
    0.82
    Activations Density 0.007%

    No Known Activations