© 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. 9-RES-JB
    11. 2273
    Prev
    Next
    INDEX
    Explanations

    phrases related to .NET technology

    oai_token-act-pair · gpt-3.5-turbo

    mentions of NET and associated software terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onym
    -0.93
    uador
    -0.87
    stown
    -0.85
    olit
    -0.82
    Reviewer
    -0.78
    iary
    -0.76
    hoe
    -0.74
    aday
    -0.74
    ãĥ´
    -0.73
    toggle
    -0.72
    POSITIVE LOGITS
     Core
    1.03
    NET
    0.89
     Framework
    0.89
    WORK
    0.88
     SDK
    0.85
     Basic
    0.84
     DirectX
    0.80
     Studio
    0.80
    ®
    0.80
     Azure
    0.79
    Activations Density 0.055%

    No Known Activations