© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 21619
    Prev
    Next
    INDEX
    Explanations

    phrases related to scheduling meetings or discussions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate delegation or meetings concerning future actions and plans

    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
     Dying
    -0.75
     disappearing
    -0.72
     Lives
    -0.71
     vanishing
    -0.70
     Falling
    -0.68
     unworthy
    -0.63
     dying
    -0.63
     Invasion
    -0.63
     stares
    -0.62
    quickShipAvailable
    -0.62
    POSITIVE LOGITS
     formulate
    1.48
     determine
    1.46
     negotiate
    1.33
     devise
    1.32
     develop
    1.31
     clarify
    1.29
     decide
    1.27
     revise
    1.27
     coordinate
    1.25
     arrange
    1.25
    Activations Density 0.293%

    No Known Activations