© 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. 9-RES-JB
    11. 6946
    Prev
    Next
    INDEX
    Explanations

    Microsoft Office related terms and technology products

    oai_token-act-pair · gpt-3.5-turbo

    keywords and terms related to Microsoft Office applications and software features

    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
    pole
    -0.79
    ãĤ©
    -0.78
    phal
    -0.73
    IGH
    -0.72
    soType
    -0.71
    ãĥ´
    -0.70
    oning
    -0.70
    rocal
    -0.70
    GBT
    -0.68
    oiler
    -0.67
    POSITIVE LOGITS
    ®
    1.02
     Suite
    0.98
     365
    0.96
     clipboard
    0.96
     Server
    0.90
    ®,
    0.88
    Office
    0.87
     plugin
    0.85
     Online
    0.84
     XP
    0.84
    Activations Density 0.115%

    No Known Activations