© 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. 10-RES-JB
    11. 12061
    Prev
    Next
    INDEX
    Explanations

    words related to spiritual concepts or practices

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Newsletter
    -0.71
    ño
    -0.71
    drops
    -0.71
    zz
    -0.70
    upon
    -0.70
    redd
    -0.70
    coat
    -0.69
    ktop
    -0.69
    CAP
    -0.68
    crop
    -0.68
    POSITIVE LOGITS
     awakening
    1.03
     communion
    1.03
    izing
    1.00
    ized
    0.97
    ising
    0.96
    ised
    0.95
     healer
    0.91
    ities
    0.91
    istic
    0.88
     cleansing
    0.88
    Activations Density 0.035%

    No Known Activations