© 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. 4-RES-JB
    11. 12072
    Prev
    Next
    INDEX
    Explanations

    mentions of specific historical locations related to World War II concentration camps

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to concentration camps

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

    No Comments

    Negative Logits
     futures
    -0.68
    drm
    -0.67
    senal
    -0.66
     kindly
    -0.66
    fml
    -0.64
    ©¶æ
    -0.64
    kefeller
    -0.64
     stocking
    -0.62
     favour
    -0.61
    Orig
    -0.61
    POSITIVE LOGITS
    akra
    1.04
    annel
    1.03
    ieving
    1.03
    rome
    0.99
    iev
    0.99
    mann
    0.90
    ieve
    0.90
    idon
    0.88
    man
    0.88
    ten
    0.85
    Activations Density 0.018%

    No Known Activations