© 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. 1-RES-JB
    11. 15693
    Prev
    Next
    INDEX
    Explanations

    references to historical and political terms related to the phrase "Third Reich."

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Reich" in historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RAW
    -0.69
    ãĥīãĥ©
    -0.67
    addons
    -0.66
    thumbnails
    -0.66
    acity
    -0.65
    ctory
    -0.65
    plates
    -0.65
     Heavenly
    -0.63
    ILA
    -0.63
     BOX
    -0.62
    POSITIVE LOGITS
     Reich
    1.26
    hardt
    1.03
    stein
    0.92
    lich
    0.87
    itzer
    0.86
    swer
    0.85
    wald
    0.81
    shire
    0.80
    enstein
    0.80
    beck
    0.79
    Activations Density 0.008%

    No Known Activations