© 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. 0-RES-JB
    11. 15380
    Prev
    Next
    INDEX
    Explanations

    the name "Lan" with variations in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Lan" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SQU
    -0.71
    È
    -0.71
    amsung
    -0.71
     nav
    -0.69
    adata
    -0.65
    weather
    -0.65
    esley
    -0.64
     dialog
    -0.64
     droid
    -0.63
    atches
    -0.62
    POSITIVE LOGITS
     Lar
    2.26
     Lan
    1.93
     Fet
    1.54
     fetus
    1.54
    fet
    1.39
     fetal
    1.34
     unborn
    1.31
     fet
    1.24
     embryo
    1.22
     Garland
    1.19
    Activations Density 0.028%

    No Known Activations