© 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. 7-RES-JB
    11. 10902
    Prev
    Next
    INDEX
    Explanations

    references to the Guantanamo Bay detention camp

    oai_token-act-pair · gpt-3.5-turbo

    references to Guantanamo Bay and its associated political and legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WN
    -0.73
     Toast
    -0.71
     EUR
    -0.70
    idas
    -0.69
     Sonic
    -0.68
     Pixie
    -0.67
     Jord
    -0.67
     ASUS
    -0.66
     EF
    -0.65
    chrom
    -0.64
    POSITIVE LOGITS
    anamo
    1.24
     detainees
    1.13
     Guantanamo
    1.08
     detainee
    1.06
     detention
    1.04
     Guant
    0.96
     Detention
    0.90
     Prison
    0.90
    prison
    0.88
    atari
    0.85
    Activations Density 0.076%

    No Known Activations