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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21595
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the operating system "Windows 10" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to Windows 10 and its various updates and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rahim
    -0.86
    rious
    -0.82
    govtrack
    -0.79
    usra
    -0.76
    rang
    -0.73
    ierrez
    -0.73
    abwe
    -0.72
    iosyncr
    -0.72
    href
    -0.72
    trump
    -0.69
    POSITIVE LOGITS
     Anniversary
    0.87
     Insider
    0.74
     desktop
    0.73
     IoT
    0.73
     2050
    0.72
     Linux
    0.72
     Ultimate
    0.71
     tablets
    0.71
     laptops
    0.70
     kernels
    0.70
    Activations Density 0.032%

    No Known Activations