© 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. 1303
    Prev
    Next
    INDEX
    Explanations

    political terms and names

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political discourse or commentary

    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
    âĢ
    -1.01
    ãĥŁ
    -0.98
    VERTISEMENT
    -0.93
    ãĤ¨ãĥ«
    -0.88
    obyl
    -0.87
     âĢ
    -0.85
    advertisement
    -0.85
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.83
    ãĤ©
    -0.83
    ãĢ
    -0.82
    POSITIVE LOGITS
     Democrats
    1.45
     Republicans
    1.44
     Obama
    1.40
     Hillary
    1.38
     Barack
    1.36
    Republicans
    1.32
     AMERICA
    1.30
     progressives
    1.29
     liberals
    1.29
     Dems
    1.28
    Activations Density 0.856%

    No Known Activations