© 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. 11-RES-JB
    11. 7823
    Prev
    Next
    INDEX
    Explanations

    keywords related to meetings and discussions

    oai_token-act-pair · gpt-3.5-turbo

    instances of meetings or discussions scheduled for various purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kinnikuman
    -0.72
    CTV
    -0.68
    TPS
    -0.64
    FX
    -0.63
     trapping
    -0.63
    Times
    -0.60
     Lives
    -0.59
     Mub
    -0.59
     collaborator
    -0.59
     disappearing
    -0.58
    POSITIVE LOGITS
     discuss
    1.57
     decide
    1.25
     determine
    1.18
     formulate
    1.14
     Discuss
    1.12
     commemorate
    1.05
     evaluate
    1.04
     propose
    1.03
     examine
    1.03
     revise
    1.03
    Activations Density 0.093%

    No Known Activations