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

    Neuronpedia

    APICircuit 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. 8389
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ton" used to describe a large quantity

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "ton" in various contexts

    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
    ELD
    -0.70
    heid
    -0.70
     Kad
    -0.67
    Known
    -0.65
     Frontier
    -0.63
     Elections
    -0.63
     Cust
    -0.62
     Journals
    -0.62
    journal
    -0.62
     Koen
    -0.62
    POSITIVE LOGITS
     ton
    1.09
    Ton
    0.96
    umen
    0.89
    aton
    0.85
    neau
    0.81
    ascus
    0.79
    oxic
    0.78
    itionally
    0.78
    othe
    0.77
     earthqu
    0.76
    Activations Density 0.006%

    No Known Activations