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. 0-RES-JB
    6. 19788
    Prev
    Next
    INDEX
    Explanations

    references to butter

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word 'butter'

    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
    rio
    -0.80
     Tra
    -0.74
    abo
    -0.70
     Xi
    -0.69
    ng
    -0.69
    Guard
    -0.69
    cd
    -0.67
     Investig
    -0.67
    Åį
    -0.67
    igi
    -0.66
    POSITIVE LOGITS
     butter
    3.62
     Butter
    2.69
     cheese
    1.44
     milk
    1.40
     toast
    1.32
     marg
    1.28
     bread
    1.26
     Cheese
    1.25
     flour
    1.23
     dairy
    1.20
    Activations Density 0.019%

    No Known Activations