© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 2775
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer operating systems, especially the term "Mac"

    oai_token-act-pair · gpt-3.5-turbo

    references to Mac computers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctr
    -0.80
    glers
    -0.71
     Bain
    -0.64
    atory
    -0.64
    atories
    -0.62
     chlorine
    -0.61
     sidx
    -0.60
     Monsanto
    -0.59
     Adin
    -0.59
    ãĥĦ
    -0.58
    POSITIVE LOGITS
    intosh
    1.44
    abre
    1.04
     OS
    1.04
    Rum
    1.04
    OS
    1.03
    Gy
    1.02
    aron
    0.98
    book
    0.97
    Book
    0.95
    donald
    0.93
    Activations Density 0.016%

    No Known Activations