© 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. 0-RES-JB
    11. 14721
    Prev
    Next
    INDEX
    Explanations

    instances of incomplete or incomplete-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to incomplete or insufficient items or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ther
    -0.67
    mob
    -0.62
    erguson
    -0.61
     clamp
    -0.60
    verts
    -0.60
    climate
    -0.60
     Dh
    -0.60
     heel
    -0.59
     shutter
    -0.59
     Yuan
    -0.59
    POSITIVE LOGITS
     incomplete
    3.14
     comple
    1.94
     unfinished
    1.59
     incom
    1.55
    teness
    1.35
    complete
    1.34
     COMPLE
    1.27
    COMPLE
    1.07
     Complete
    0.97
     imperfect
    0.96
    Activations Density 0.027%

    No Known Activations