© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 21502
    Prev
    Next
    INDEX
    Explanations

    keywords related to Microsoft Office applications, specifically Excel, PowerPoint, and Word

    oai_token-act-pair · gpt-3.5-turbo

    references to Microsoft Office applications and related software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phal
    -0.84
    ablishment
    -0.81
    pole
    -0.77
    raising
    -0.76
    bh
    -0.76
    ãĤ©
    -0.75
    IGH
    -0.73
    tarians
    -0.69
    heny
    -0.68
     rab
    -0.68
    POSITIVE LOGITS
     Plugin
    1.12
     Tools
    1.10
     Photoshop
    1.09
     PowerPoint
    1.08
    Tool
    1.05
     Suite
    1.05
     Excel
    1.05
     IDE
    1.04
    TeX
    1.03
     plugin
    1.03
    Activations Density 0.145%

    No Known Activations