© 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. 18768
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to male individuals with the title "Mr." followed by a name

    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
     actionGroup
    -0.78
    ãĥ´ãĤ¡
    -0.72
    rawdownloadcloneembedreportprint
    -0.63
    ãĥ¼ãĥĨ
    -0.63
    ebook
    -0.62
    âĦ¢:
    -0.60
    20439
    -0.59
    Women
    -0.59
     downt
    -0.59
     Lutheran
    -0.59
    POSITIVE LOGITS
    ertodd
    0.90
    Mr
    0.89
    unal
    0.88
     Mr
    0.80
    ctuary
    0.79
    hesis
    0.76
    cipled
    0.74
     Farage
    0.73
    ierrez
    0.73
    ovych
    0.72
    Activations Density 0.026%

    No Known Activations