© 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. 2-RES-JB
    11. 12676
    Prev
    Next
    INDEX
    Explanations

    the word "bur" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "burrow."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įå
    -0.87
    éĹĺ
    -0.85
     Regulatory
    -0.76
    aunder
    -0.69
    姫
    -0.68
     Failure
    -0.68
    payer
    -0.68
    )=(
    -0.68
    OA
    -0.68
    DragonMagazine
    -0.67
    POSITIVE LOGITS
     bur
    1.19
    rows
    1.15
    rito
    1.14
    rowing
    1.09
    row
    0.94
    rette
    0.93
    gey
    0.92
    querque
    0.91
    ried
    0.90
    geons
    0.90
    Activations Density 0.004%

    No Known Activations