© 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. 6-RES-JB
    11. 3104
    Prev
    Next
    INDEX
    Explanations

    the word "whole" followed by various contexts or word combinations

    oai_token-act-pair · gpt-3.5-turbo

    references to "whole" both in terms of food and broader contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eer
    -0.74
    KER
    -0.68
    rf
    -0.65
    eers
    -0.65
     Prel
    -0.62
    interstitial
    -0.62
    geon
    -0.62
     Superintendent
    -0.61
    yip
    -0.60
     Specialist
    -0.59
    POSITIVE LOGITS
    heartedly
    1.70
    hearted
    1.33
    meal
    0.85
     darn
    0.83
     damn
    0.81
     freaking
    0.75
    ãĤ¨ãĥ«
    0.75
    hands
    0.74
     thing
    0.73
    allo
    0.70
    Activations Density 0.019%

    No Known Activations