© 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. 18466
    Prev
    Next
    INDEX
    Explanations

    names or titles with 'Mr.' before them

    oai_token-act-pair · gpt-3.5-turbo

    references to 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 @ 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
     actionGroup
    -0.85
    20439
    -0.69
    ãĥ¼ãĥĨ
    -0.69
    ãĥ´ãĤ¡
    -0.66
    Women
    -0.66
    Especially
    -0.64
     Compared
    -0.61
     downt
    -0.60
    Ranked
    -0.60
    rawdownloadcloneembedreportprint
    -0.60
    POSITIVE LOGITS
    unal
    0.89
    ctuary
    0.77
    acket
    0.77
    angelo
    0.74
    hesis
    0.73
     Universe
    0.72
    ths
    0.71
    entle
    0.71
     Brother
    0.70
    uitous
    0.69
    Activations Density 0.027%

    No Known Activations