© 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. 0-RES-JB
    11. 19177
    Prev
    Next
    INDEX
    Explanations

    references to a specific group or entity called "The Nation."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Nation"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     directions
    -0.71
    lled
    -0.66
    boxes
    -0.66
     sweets
    -0.63
     "<
    -0.62
     angled
    -0.61
     satisfying
    -0.59
    lling
    -0.59
     circular
    -0.58
     hiding
    -0.57
    POSITIVE LOGITS
     Nation
    4.30
    Nation
    2.62
     Nations
    1.90
     nation
    1.59
    nation
    1.58
     Tribe
    1.34
     Country
    1.25
     States
    1.10
     Republic
    1.00
    National
    0.98
    Activations Density 0.007%

    No Known Activations