© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 7033
    Prev
    Next
    INDEX
    Explanations

    references to the country Yemen

    oai_token-act-pair · gpt-3.5-turbo

    references to Yemen and related political or military contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LAPD
    -0.73
     Gunn
    -0.69
     Lovecraft
    -0.69
     Wonderland
    -0.67
     cones
    -0.67
     Chloe
    -0.66
     Vegas
    -0.66
     Vita
    -0.65
     Compton
    -0.63
     Canaver
    -0.63
    POSITIVE LOGITS
    beans
    0.94
    ites
    0.91
    is
    0.90
    isi
    0.89
    aina
    0.85
    ilit
    0.85
    ite
    0.83
    istani
    0.83
     Houth
    0.82
    oha
    0.79
    Activations Density 0.050%

    No Known Activations