© 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. 4-RES-JB
    11. 10605
    Prev
    Next
    INDEX
    Explanations

    terms related to religious topics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to religious beliefs and their implications

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

    No Comments

    Negative Logits
     Lans
    -1.01
    agher
    -0.85
    ufact
    -0.84
    20439
    -0.82
     Tunnel
    -0.77
    aunder
    -0.73
    hyde
    -0.72
    æ©
    -0.71
    assetsadobe
    -0.70
     Wilde
    -0.69
    POSITIVE LOGITS
     affili
    1.00
     affiliation
    0.95
     zeal
    0.90
     fundamental
    0.89
     beliefs
    0.89
     liberties
    0.86
     faiths
    0.86
     freedom
    0.86
     rites
    0.85
     liberty
    0.83
    Activations Density 0.020%

    No Known Activations