© 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. 4894
    Prev
    Next
    INDEX
    Explanations

    mentions of political extremist groups and ideologies, specifically related to neo-Nazis

    oai_token-act-pair · gpt-3.5-turbo

    mentions of neo-Nazi groups and related 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
     emoji
    -0.77
     outp
    -0.76
     bets
    -0.74
     overdue
    -0.73
     unlocking
    -0.73
     accompanying
    -0.72
     exerc
    -0.72
     hereby
    -0.69
     contacting
    -0.69
     congratulations
    -0.69
    POSITIVE LOGITS
    Nazi
    1.61
    Nazis
    1.59
    liberal
    1.43
    fascist
    1.43
    colonial
    1.35
    natal
    1.27
    Naz
    1.27
    conservative
    1.26
    Conf
    1.19
    Marx
    1.18
    Activations Density 0.034%

    No Known Activations