© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 24552
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "milk" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to milk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Manuel
    -0.76
    SPONSORED
    -0.74
     Exile
    -0.69
    vernment
    -0.68
    ISE
    -0.67
     lawy
    -0.66
    âĸ¬
    -0.64
    OPLE
    -0.62
     resil
    -0.62
    RM
    -0.62
    POSITIVE LOGITS
    weed
    1.40
    maid
    1.12
     chocolate
    0.99
     milk
    0.98
    beans
    0.96
    mil
    0.94
    fed
    0.94
    fat
    0.92
    cup
    0.91
    bean
    0.91
    Activations Density 0.031%

    No Known Activations