© 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. 10-RES-JB
    11. 11279
    Prev
    Next
    INDEX
    Explanations

    terms related to extremist ideologies or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to neo-Nazi ideology and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hereby
    -0.76
     bets
    -0.73
     inhal
    -0.72
     contacting
    -0.72
     emoji
    -0.72
     overdue
    -0.71
     outstanding
    -0.71
     outp
    -0.71
     accompanying
    -0.71
     iT
    -0.68
    POSITIVE LOGITS
    Nazi
    1.61
    Nazis
    1.50
    liberal
    1.50
    fascist
    1.34
    femin
    1.30
    colonial
    1.27
    conservative
    1.24
    liber
    1.24
    radical
    1.17
    natal
    1.17
    Activations Density 0.028%

    No Known Activations