© 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. 14133
    Prev
    Next
    INDEX
    Explanations

    mentions of specific groups like businessmen, policymakers, veterans, families, workers, priests, bishops, inmates, leaders, soldiers, police chiefs, officers, and professionals within a context of communication or interaction

    oai_token-act-pair · gpt-3.5-turbo

    references to audiences and groups of people, particularly in formal or professional contexts

    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
    theless
    -0.67
     conviction
    -0.64
    Ħ¢
    -0.63
    Drive
    -0.63
    Sense
    -0.62
     Syndrome
    -0.58
     Presence
    -0.57
    Õ
    -0.57
     itself
    -0.57
    Pause
    -0.56
    POSITIVE LOGITS
     gathered
    1.17
     attending
    1.14
     stationed
    1.01
    folk
    0.93
     assembled
    0.92
     visiting
    0.90
    hips
    0.89
     protesting
    0.89
     celebrating
    0.88
     vying
    0.87
    Activations Density 0.298%

    No Known Activations