© 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. 2-RES-JB
    11. 12419
    Prev
    Next
    INDEX
    Explanations

    the word "whole" as an indication of encompassing or complete aspects within a context

    oai_token-act-pair · gpt-3.5-turbo

    the word "whole" in various contexts

    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
    Blade
    -0.72
    yip
    -0.70
    cl
    -0.62
     Superintendent
    -0.61
     Cutter
    -0.58
    estamp
    -0.58
    minist
    -0.56
    geon
    -0.56
    KER
    -0.56
    tips
    -0.56
    POSITIVE LOGITS
    heartedly
    1.52
    hearted
    1.07
    oton
    0.74
     gam
    0.74
    ciating
    0.73
     darn
    0.72
     freaking
    0.71
    ãĤ¨ãĥ«
    0.69
     damn
    0.68
     Godd
    0.68
    Activations Density 0.022%

    No Known Activations