© 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. 5048
    Prev
    Next
    INDEX
    Explanations

    words related to specific names in politics, technology, and events

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals and organizations

    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
     Bosnia
    -0.94
     Serbian
    -0.82
     Croatian
    -0.77
     SU
    -0.76
    ãĥ¼ãĥĨãĤ£
    -0.75
     Serbia
    -0.73
    addon
    -0.72
    entry
    -0.70
     Croatia
    -0.69
    Benz
    -0.68
    POSITIVE LOGITS
     Dew
    2.90
    onew
    1.32
     Hancock
    1.28
     Iro
    1.16
     Crow
    1.16
     Ripple
    1.14
     Louie
    1.13
     Gaw
    1.07
     Hawkins
    1.06
     Rousse
    1.02
    Activations Density 0.048%

    No Known Activations