© 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 EvalsExportsinterp-engineNEWAPI 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. 20792
    Prev
    Next
    INDEX
    Explanations

    terms related to the Guantanamo Bay detention camp

    oai_token-act-pair · gpt-3.5-turbo

    references to Guantanamo and its related context

    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
     Franch
    -0.70
    WN
    -0.69
    theless
    -0.68
     NRS
    -0.67
    é¾įå
    -0.67
    Ü
    -0.67
    BY
    -0.66
    RY
    -0.66
    KY
    -0.66
    Merit
    -0.65
    POSITIVE LOGITS
     Guantanamo
    1.17
    anamo
    1.15
     Guant
    1.08
     detainees
    0.96
     detention
    0.86
    ilitation
    0.85
    heed
    0.83
     detainee
    0.82
    querque
    0.82
    illo
    0.81
    Activations Density 0.005%

    No Known Activations