© 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. 2-RES-JB
    11. 21966
    Prev
    Next
    INDEX
    Explanations

    instances where dedication or commitment to a specific cause or purpose is expressed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dedicated."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ain
    -0.91
     Solomon
    -0.72
    Rus
    -0.70
     Luk
    -0.70
     Takeru
    -0.69
     Shan
    -0.69
     Awakening
    -0.67
     Monica
    -0.67
    java
    -0.66
     Elephant
    -0.66
    POSITIVE LOGITS
     dedicated
    1.06
     IPM
    0.95
     devoted
    0.94
     dedicate
    0.93
    rontal
    0.83
    ricular
    0.75
     duty
    0.73
    duty
    0.73
    interstitial
    0.72
     ded
    0.72
    Activations Density 0.013%

    No Known Activations