Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 5211
    Prev
    Next
    INDEX
    Explanations

    keywords related to different versions of Windows operating system

    oai_token-act-pair · gpt-3.5-turbo

    mentions 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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eca
    -0.81
    onies
    -0.78
    OHN
    -0.75
    asure
    -0.72
    ritz
    -0.72
    asin
    -0.71
    oning
    -0.71
    olesc
    -0.70
    taker
    -0.67
    ischer
    -0.67
    POSITIVE LOGITS
     Vista
    1.10
     PowerShell
    1.06
     XP
    1.03
     Defender
    0.97
     Phone
    0.96
    XP
    0.93
     Azure
    0.91
     Explorer
    0.88
     DirectX
    0.87
     Server
    0.86
    Activations Density 0.023%

    No Known Activations