© 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. 3-RES-JB
    11. 3110
    Prev
    Next
    INDEX
    Explanations

    mentions of different versions of the Windows operating system

    oai_token-act-pair · gpt-3.5-turbo

    references to different versions of the Windows operating system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yss
    -0.82
    ãĥ©ãĥ³
    -0.77
    onies
    -0.76
    oning
    -0.74
    omas
    -0.74
    agher
    -0.74
    displayText
    -0.71
    ritz
    -0.71
    OHN
    -0.70
    asin
    -0.69
    POSITIVE LOGITS
     PowerShell
    1.08
     Azure
    0.98
     Vista
    0.97
     Explorer
    0.92
    WINDOWS
    0.90
    Windows
    0.88
     DirectX
    0.87
     XP
    0.85
     Windows
    0.84
    XP
    0.78
    Activations Density 0.014%

    No Known Activations