© 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. 20790
    Prev
    Next
    INDEX
    Explanations

    phrases related to war, conflict, and atrocities

    oai_token-act-pair · gpt-3.5-turbo

    references to historical atrocities related to concentration camps and forced labor

    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
    wcsstore
    -0.84
    soDeliveryDate
    -0.75
     WS
    -0.71
     Toast
    -0.69
     RC
    -0.67
    VP
    -0.67
     Prediction
    -0.67
    ASH
    -0.67
    Shares
    -0.66
     Drivers
    -0.66
    POSITIVE LOGITS
     Auschwitz
    1.24
     inmates
    1.07
     detainees
    1.05
    chwitz
    1.04
     torture
    1.03
     confinement
    0.99
     dehuman
    0.99
     Holocaust
    0.98
    ocaust
    0.97
     gul
    0.96
    Activations Density 0.139%

    No Known Activations