© 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. 4-RES-JB
    11. 4878
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Guantanamo Bay detention camp

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Guantanamo Bay and related locations

    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
    Merit
    -0.83
    WN
    -0.74
     Pixie
    -0.70
     Franch
    -0.69
    theless
    -0.68
    nings
    -0.65
     WB
    -0.64
    KY
    -0.63
     Jord
    -0.62
    pg
    -0.61
    POSITIVE LOGITS
     Guant
    1.10
    anamo
    1.07
     Guantanamo
    1.05
    querque
    0.86
     detainees
    0.86
     Hussein
    0.86
    ghan
    0.83
    heed
    0.81
     detention
    0.80
     confinement
    0.77
    Activations Density 0.008%

    No Known Activations