© 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. 4-RES-JB
    11. 23705
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning actions related to windows

    oai_token-act-pair · gpt-3.5-turbo

    references to "windows"

    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
    ghan
    -0.82
    Downloadha
    -0.78
    doms
    -0.76
    ometown
    -0.73
    avez
    -0.72
     Flavoring
    -0.71
    zin
    -0.70
    icient
    -0.70
    agonist
    -0.70
     Haram
    -0.70
    POSITIVE LOGITS
     pane
    1.01
     window
    0.97
    glass
    0.96
     windows
    0.95
     sill
    0.94
     wip
    0.91
     Window
    0.89
    window
    0.87
     ledge
    0.82
    edin
    0.79
    Activations Density 0.009%

    No Known Activations