© 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. 9-RES-JB
    11. 2241
    Prev
    Next
    INDEX
    Explanations

    mentions of different religious groups and beliefs

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assetsadobe
    -1.17
    Crash
    -0.98
    Layer
    -0.87
    trap
    -0.84
     Crash
    -0.83
    ridor
    -0.82
    hazard
    -0.82
    \/\/
    -0.79
    daq
    -0.79
     Velocity
    -0.78
    POSITIVE LOGITS
     Christianity
    1.84
     religious
    1.79
     Judaism
    1.78
     Protestant
    1.78
     theology
    1.76
     church
    1.76
     churches
    1.75
     Catholicism
    1.73
     Catholic
    1.72
     pagan
    1.72
    Activations Density 1.005%

    No Known Activations