© 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. 9309
    Prev
    Next
    INDEX
    Explanations

    references to Republican politicians and related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Republican party

    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
    krit
    -0.80
    adr
    -0.79
    ortmund
    -0.78
    trak
    -0.73
    variable
    -0.71
    pots
    -0.69
    kok
    -0.69
    ijk
    -0.69
    ensitive
    -0.69
     Myster
    -0.69
    POSITIVE LOGITS
     Party
    1.04
     strongh
    0.96
     stronghold
    0.92
     majorities
    0.92
     frontrunner
    0.87
     presidential
    0.86
     hopeful
    0.86
     nominee
    0.85
     orthodoxy
    0.85
     incumbent
    0.83
    Activations Density 0.040%

    No Known Activations