© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3-RES-JB
    11. 17231
    Prev
    Next
    INDEX
    Explanations

    terms related to right-wing politics

    oai_token-act-pair · gpt-3.5-turbo

    references to right-wing ideologies and groups

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    BILITIES
    -0.80
     LIA
    -0.75
     Kear
    -0.72
     Butcher
    -0.72
     Exhibition
    -0.68
     Lakes
    -0.67
     Collection
    -0.67
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
    è¦ļéĨĴ
    -0.64
    ãĤ¨ãĥ«
    -0.64
    POSITIVE LOGITS
     extremists
    1.15
     extremism
    1.12
     extremist
    1.11
     radicals
    1.05
     orthodoxy
    0.92
     populism
    0.92
     adherents
    0.91
     ide
    0.91
     activists
    0.88
     ideology
    0.88
    Activations Density 0.031%

    No Known Activations