© 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. 2-RES-JB
    11. 17682
    Prev
    Next
    INDEX
    Explanations

    references to historical figures related to war and political ideology, specifically focusing on Adolf Hitler

    oai_token-act-pair · gpt-3.5-turbo

    references to Adolf Hitler and related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SHARE
    -0.71
    tis
    -0.71
    Self
    -0.71
    Dub
    -0.70
    Sleep
    -0.69
    Asia
    -0.68
    Sources
    -0.68
    Pac
    -0.68
    Medium
    -0.68
    ilver
    -0.68
    POSITIVE LOGITS
     Hitler
    1.07
    enstein
    0.90
    dinand
    0.90
    olini
    0.88
    geist
    0.85
     salute
    0.84
    oleon
    0.84
    abad
    0.82
    umenthal
    0.81
     indoctr
    0.79
    Activations Density 0.015%

    No Known Activations