Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 14035
    Prev
    Next
    INDEX
    Explanations

    names or references related to Adolf Hitler

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Adolf Hitler and related references in historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NESS
    -0.72
    RC
    -0.69
    CT
    -0.69
     mesh
    -0.68
    VC
    -0.68
     providers
    -0.67
     quad
    -0.67
    LV
    -0.67
    Provider
    -0.66
     const
    -0.66
    POSITIVE LOGITS
     Hitler
    3.66
     Adolf
    2.49
     Nazi
    2.45
     Nazis
    2.25
    Nazi
    2.01
     Stalin
    1.99
     Auschwitz
    1.88
     fascism
    1.78
     fascist
    1.70
     Holocaust
    1.67
    Activations Density 0.023%

    No Known Activations