© 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. 3657
    Prev
    Next
    INDEX
    Explanations

    words related to location endings, specifically "une."

    oai_token-act-pair · gpt-3.5-turbo

    the word "une" 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
    ories
    -0.79
     teasp
    -0.79
    lished
    -0.72
    loo
    -0.72
    addock
    -0.68
    İĭ
    -0.67
    ¶ħ
    -0.67
    iences
    -0.67
    psc
    -0.64
    ijk
    -0.64
    POSITIVE LOGITS
    une
    1.26
    arthed
    0.88
    UNE
    0.73
    aber
    0.68
     Yak
    0.65
     immunity
    0.65
    uly
    0.63
    quist
    0.63
    uma
    0.62
     Mik
    0.61
    Activations Density 0.010%

    No Known Activations