© 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. 11-RES-JB
    11. 7134
    Prev
    Next
    INDEX
    Explanations

    mentions of historical events related to war, specifically World War II

    oai_token-act-pair · gpt-3.5-turbo
    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
     sher
    -0.71
    OGR
    -0.68
    APS
    -0.67
    say
    -0.65
    doi
    -0.65
    QUI
    -0.63
    DEF
    -0.62
     prosecut
    -0.62
     predictive
    -0.61
    ITY
    -0.60
    POSITIVE LOGITS
     II
    1.36
     Two
    1.12
     III
    1.08
     XII
    0.95
     Three
    0.92
     ii
    0.90
     1942
    0.88
     XVI
    0.88
     VII
    0.86
    planes
    0.85
    Activations Density 0.021%

    No Known Activations