© 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. 11-RES-JB
    11. 20365
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations, organizations, and events

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of locations, organizations, and prominent figures

    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
     whilst
    -0.78
    âĢ¦.
    -0.74
    chwitz
    -0.74
    nob
    -0.73
    ..
    -0.71
    ....
    -0.71
    [_
    -0.71
    *****
    -0.71
     ..
    -0.70
    *.
    -0.70
    POSITIVE LOGITS
     spokeswoman
    1.08
     spokesman
    1.06
     spokesperson
    1.05
     Tribune
    0.97
     duo
    0.97
     Gazette
    0.96
     group
    0.96
     lawmaker
    0.96
     incident
    0.96
     trio
    0.94
    Activations Density 0.359%

    No Known Activations