© 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. 3-RES-JB
    11. 685
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and code, specifically related to the "sub" function

    oai_token-act-pair · gpt-3.5-turbo

    programming or coding terminology

    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
    VW
    -0.76
    abl
    -0.76
    iHUD
    -0.75
    lev
    -0.73
    engu
    -0.71
    ND
    -0.70
    JP
    -0.70
    RF
    -0.69
    otto
    -0.68
    amer
    -0.68
    POSITIVE LOGITS
     Cosmos
    0.78
    maid
    0.77
     Patriarch
    0.70
     Instruments
    0.68
     Sandwich
    0.68
     Inquisitor
    0.68
     Syri
    0.67
     Compan
    0.67
     Commun
    0.65
     Binary
    0.65
    Activations Density 0.000%

    No Known Activations