© 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. 18315
    Prev
    Next
    INDEX
    Explanations

    phrases or contexts related to the concept of "window."

    oai_token-act-pair · gpt-3.5-turbo

    references to "window" as a concept of opportunity or time frame

    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
    ghan
    -0.91
    IGH
    -0.81
    otin
    -0.78
    ORN
    -0.69
    amaru
    -0.69
    zin
    -0.68
     Flavoring
    -0.68
    ortium
    -0.68
    icient
    -0.68
     unnatural
    -0.67
    POSITIVE LOGITS
     window
    1.02
     windows
    0.97
    window
    0.96
     Window
    0.93
     pane
    0.91
     sill
    0.88
     wip
    0.81
     opener
    0.80
    windows
    0.79
    glass
    0.76
    Activations Density 0.007%

    No Known Activations