© 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. 3733
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Mill"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Mill" in various contexts

    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
     offending
    -0.72
     coordinated
    -0.70
     compelling
    -0.68
     appeals
    -0.68
     stern
    -0.66
     manifest
    -0.66
     careful
    -0.65
     venom
    -0.65
     fierce
    -0.65
     personalized
    -0.65
    POSITIVE LOGITS
    enium
    1.52
     Mill
    1.12
    isec
    1.07
    icent
    1.03
    igans
    1.03
    imet
    1.03
    itary
    1.02
    mill
    1.01
    inery
    0.98
    Mill
    0.97
    Activations Density 0.005%

    No Known Activations