© 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. 10-RES-JB
    11. 13966
    Prev
    Next
    INDEX
    Explanations

    action verbs in past tense

    oai_token-act-pair · gpt-3.5-turbo

    action-oriented verbs related to events, achievements, or contributions

    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
    SPONSORED
    -0.79
    POSE
    -0.72
    itte
    -0.69
    iffe
    -0.69
    cipled
    -0.64
    å¦
    -0.64
    enos
    -0.64
    hatt
    -0.62
    ç«
    -0.62
    ãģĨ
    -0.61
    POSITIVE LOGITS
     by
    1.45
     BY
    1.00
     By
    0.94
    by
    0.92
    By
    0.90
     aback
    0.87
    bys
    0.85
     therein
    0.71
     herein
    0.70
     me
    0.64
    Activations Density 0.388%

    No Known Activations