© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3344
    Prev
    Next
    INDEX
    Explanations

    groups of people

    oai_token-act-pair · gpt-3.5-turbo

    the term "group" followed by a numerical identifier, indicating collective entities or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wards
    -0.61
    Bloomberg
    -0.58
    wrapper
    -0.58
     Dame
    -0.57
    WS
    -0.56
    èª
    -0.55
     straight
    -0.54
     vap
    -0.53
    stroke
    -0.53
    alli
    -0.53
    POSITIVE LOGITS
    think
    1.19
    leader
    0.94
    ings
    0.93
    members
    0.90
     disbanded
    0.86
     membership
    0.82
     members
    0.81
    ages
    0.79
    affiliated
    0.79
     affili
    0.77
    Activations Density 0.070%

    No Known Activations