© 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. 11-RES-JB
    11. 20529
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Mil" with varying activation levels

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Mil" and its variations in a context that suggests importance or relevance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LY
    -0.66
     THREE
    -0.66
     depreciation
    -0.65
     damned
    -0.64
    nces
    -0.64
    OPLE
    -0.62
     brace
    -0.61
    YE
    -0.60
     aroused
    -0.57
    ORTS
    -0.57
    POSITIVE LOGITS
    estones
    1.49
    estone
    1.38
    waukee
    1.33
    ksh
    1.29
    itant
    1.22
    isec
    1.17
    gram
    1.15
    ieu
    1.07
    itar
    1.07
    pit
    1.04
    Activations Density 0.027%

    No Known Activations