© 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. 6-RES-JB
    11. 9413
    Prev
    Next
    INDEX
    Explanations

    the name "Bernie Sanders"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name Bernie Sanders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otropic
    -0.79
    obar
    -0.77
     tyr
    -0.77
    ãĥ¼ãĥĨãĤ£
    -0.76
    perm
    -0.75
    omaly
    -0.73
     Instr
    -0.71
    ebin
    -0.71
    bodied
    -0.69
     destro
    -0.68
    POSITIVE LOGITS
     Sanders
    1.36
    Sanders
    0.98
     Supporters
    0.90
     Bernard
    0.90
    Bernie
    0.82
    INTON
    0.81
     supporters
    0.80
     Bros
    0.80
     Bernie
    0.78
     Caucus
    0.78
    Activations Density 0.011%

    No Known Activations