© 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 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. 19628
    Prev
    Next
    INDEX
    Explanations

    the name "Mr." followed by another word

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals, specifically those with the title "Mr." followed by their names or initials

    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
    -0.87
    rawdownloadcloneembedreportprint
    -0.78
    ãĥ¼ãĥĨ
    -0.76
    Women
    -0.72
    SHIP
    -0.68
    VALUE
    -0.68
    dylib
    -0.66
    ENDED
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.65
     Compared
    -0.64
    POSITIVE LOGITS
    unal
    0.78
     Universe
    0.72
     Hussein
    0.68
    iggs
    0.66
    ufact
    0.64
    orters
    0.64
    ctuary
    0.64
     Claus
    0.64
    ong
    0.62
     Gor
    0.62
    Activations Density 0.027%

    No Known Activations