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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 3953
    Prev
    Next
    INDEX
    Explanations

    mentions of milk or words related to milk

    oai_token-act-pair · gpt-3.5-turbo

    references to milk or milk-related products

    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
     Unch
    -0.71
     Warriors
    -0.69
    ORTS
    -0.68
     Sins
    -0.66
     CARD
    -0.66
     Result
    -0.65
    BOOK
    -0.64
     Fear
    -0.64
     Errors
    -0.64
    OPLE
    -0.63
    POSITIVE LOGITS
     mil
    1.16
    isec
    0.98
    ieu
    0.98
    waukee
    0.94
    mil
    0.93
    ksh
    0.92
    fed
    0.85
    vin
    0.79
    enium
    0.78
    quet
    0.77
    Activations Density 0.004%

    No Known Activations