© 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. 3-RES-JB
    11. 676
    Prev
    Next
    INDEX
    Explanations

    references to famous historical and philosophical figures

    oai_token-act-pair · gpt-3.5-turbo

    references to historical figures and concepts related to aristocracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à©
    -0.81
    ned
    -0.79
    aneously
    -0.78
    LOD
    -0.77
    ning
    -0.73
     Fraser
    -0.71
    lights
    -0.71
    FE
    -0.69
     McKenzie
    -0.68
    LA
    -0.68
    POSITIVE LOGITS
    ocrats
    1.46
    ocrat
    1.35
    ocratic
    1.33
     Arist
    1.04
    ocr
    0.98
    anqu
    0.89
     theoret
    0.87
     welf
    0.87
    iosyn
    0.86
    ocracy
    0.84
    Activations Density 0.018%

    No Known Activations