© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 2080
    Prev
    Next
    INDEX
    Explanations

    references to far-right and extremist political ideologies

    oai_token-act-pair · gpt-3.5-turbo

    references to neo-Nazi ideologies or groups

    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
    ecause
    -0.68
    lessly
    -0.65
    lain
    -0.62
    hips
    -0.60
    ourcing
    -0.60
     balloons
    -0.58
    lifting
    -0.58
     mishand
    -0.58
    ricular
    -0.58
    lio
    -0.57
    POSITIVE LOGITS
    ethical
    0.89
    Nazi
    0.87
    cephal
    0.84
    femin
    0.83
    -)
    0.81
    -
    0.80
    Nazis
    0.79
    fascist
    0.78
    hist
    0.77
    -[
    0.77
    Activations Density 0.030%

    No Known Activations