© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 12110
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events and places, especially related to the Reich

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Reich" and related historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.74
     Tibetan
    -0.69
    ctica
    -0.69
    RAW
    -0.66
    ILA
    -0.66
    Hop
    -0.65
    acity
    -0.65
    Dub
    -0.65
     BOX
    -0.65
    abetic
    -0.64
    POSITIVE LOGITS
     Reich
    1.09
    hardt
    1.07
    stein
    1.01
    lich
    0.88
     decree
    0.84
    shire
    0.81
    wald
    0.81
    heimer
    0.80
    enstein
    0.80
    itzer
    0.80
    Activations Density 0.010%

    No Known Activations