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. 5-RES-JB
    6. 4914
    Prev
    Next
    INDEX
    Explanations

    mentions and instructions related to the ingredient "butter"

    oai_token-act-pair · gpt-3.5-turbo

    references to butter and its usage in cooking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vernment
    -0.96
    SPONSORED
    -0.73
     Exile
    -0.70
    ostics
    -0.67
     Naz
    -0.65
     debtor
    -0.64
     Citizen
    -0.63
    OPLE
    -0.63
    ollow
    -0.62
     Fundamental
    -0.62
    POSITIVE LOGITS
    cream
    1.33
    flies
    1.15
    cup
    1.04
    maid
    0.96
    beer
    0.96
    fat
    0.96
    stroke
    0.94
    worth
    0.91
    bowl
    0.91
    riter
    0.90
    Activations Density 0.019%

    No Known Activations