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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 126
    Prev
    Next
    INDEX
    Explanations

    the word "trophy"

    oai_token-act-pair · gpt-4-turbo

    mentions of the word "trophy."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "trophy" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    utenberg
    -0.83
    lement
    -0.71
    weeney
    -0.70
    trak
    -0.69
    andem
    -0.69
    early
    -0.68
    olen
    -0.68
    iasco
    -0.66
     hypers
    -0.65
     experimenting
    -0.65
    POSITIVE LOGITS
     trophy
    1.30
     Trophy
    1.28
     trophies
    1.20
    phies
    1.02
     Rica
    0.89
    ilage
    0.75
     medal
    0.74
     awards
    0.72
    cakes
    0.71
    Congratulations
    0.69
    Activations Density 0.006%

    No Known Activations