© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5866
    Prev
    Next
    INDEX
    Explanations

    phrases related to political campaigns and candidates

    oai_token-act-pair · gpt-3.5-turbo

    references to political candidates and their respective parties

    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
    english
    -0.83
    nikov
    -0.78
     cs
    -0.72
    sky
    -0.71
    netflix
    -0.69
     CLSID
    -0.68
    ãĥĥ
    -0.67
    Explore
    -0.67
    nexus
    -0.65
     coh
    -0.65
    POSITIVE LOGITS
     Mitt
    1.51
     Hillary
    1.51
     Donald
    1.39
     Bernie
    1.32
    Hillary
    1.31
     Jeb
    1.29
     Barack
    1.26
     Marco
    1.25
     Jill
    1.19
     Newt
    1.18
    Activations Density 0.130%

    No Known Activations