© 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. 4-RES-JB
    11. 10381
    Prev
    Next
    INDEX
    Explanations

    proper nouns preceded by "Mr." in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to male characters or individuals named "Mr."

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

    No Comments

    Negative Logits
     actionGroup
    -0.82
    rawdownloadcloneembedreportprint
    -0.74
    ãĥ¼ãĥĨ
    -0.74
     destro
    -0.70
    SHIP
    -0.69
    catentry
    -0.65
    anwhile
    -0.65
     cruc
    -0.65
     conduc
    -0.61
    Especially
    -0.61
    POSITIVE LOGITS
     Universe
    0.86
    angelo
    0.73
     Incredible
    0.70
     Claus
    0.69
    imen
    0.67
    acket
    0.66
    ude
    0.65
    gery
    0.63
     Neighbor
    0.63
    ctuary
    0.62
    Activations Density 0.034%

    No Known Activations