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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 18256
    Prev
    Next
    INDEX
    Explanations

    words related to the term "Mill"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Mill."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     manifest
    -0.73
     compr
    -0.69
     familiar
    -0.66
     coordinated
    -0.66
     offending
    -0.66
     effected
    -0.66
     arous
    -0.65
     compelling
    -0.65
     screened
    -0.64
     endemic
    -0.63
    POSITIVE LOGITS
    enium
    1.64
    igans
    1.19
    imet
    1.17
    isec
    1.17
    icent
    1.10
    inery
    1.08
    itary
    1.07
    enn
    1.06
    iard
    1.06
    stones
    1.02
    Activations Density 0.007%

    No Known Activations