© 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. 7706
    Prev
    Next
    INDEX
    Explanations

    words related to right-wing political ideologies and groups

    oai_token-act-pair · gpt-3.5-turbo

    references to right-wing politics and ideologies

    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
     Pell
    -0.66
     Prol
    -0.64
    ãĤ¼ãĤ¦ãĤ¹
    -0.64
     pudding
    -0.62
     transact
    -0.61
     flux
    -0.61
     dism
    -0.60
     KH
    -0.60
     Feder
    -0.60
     disappoint
    -0.60
    POSITIVE LOGITS
    wing
    1.67
    leaning
    1.63
    hander
    1.59
    handed
    1.57
    thinking
    1.39
    angled
    1.33
    Wing
    1.33
    hand
    1.29
    behind
    1.27
    sided
    1.24
    Activations Density 0.034%

    No Known Activations