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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 12761
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the word "milk"

    oai_token-act-pair · gpt-3.5-turbo

    references to milk, particularly in various contexts and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angers
    -0.79
    SPONSORED
    -0.79
    vernment
    -0.74
    izons
    -0.74
    ISE
    -0.73
    âĸ¬
    -0.68
    iannopoulos
    -0.67
    asio
    -0.67
     satell
    -0.66
     lawy
    -0.66
    POSITIVE LOGITS
    weed
    1.26
    waukee
    1.07
    maid
    1.03
    fed
    0.91
    erton
    0.90
     milk
    0.90
    tub
    0.89
     Milk
    0.88
    mil
    0.86
     chocolate
    0.86
    Activations Density 0.025%

    No Known Activations