© 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. 0-RES-JB
    11. 11357
    Prev
    Next
    INDEX
    Explanations

    mentions of different versions of Windows

    oai_token-act-pair · gpt-3.5-turbo

    mentions of operating systems and their versions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Barker
    -0.84
    agher
    -0.77
    aez
    -0.77
    IER
    -0.74
    amide
    -0.72
     Daly
    -0.70
    cart
    -0.70
    igne
    -0.70
    kef
    -0.70
     Huss
    -0.69
    POSITIVE LOGITS
     Windows
    3.29
    Windows
    2.61
    windows
    2.18
     Microsoft
    1.97
     Lumia
    1.78
     Linux
    1.78
    Microsoft
    1.77
     Ubuntu
    1.74
     macOS
    1.69
    WINDOWS
    1.63
    Activations Density 0.009%

    No Known Activations