© 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. 8-RES-JB
    11. 4241
    Prev
    Next
    INDEX
    Explanations

    mentions of places of worship, particularly churches

    oai_token-act-pair · gpt-3.5-turbo

    references to churches and related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rog
    -0.68
    schild
    -0.63
     neurot
    -0.61
    Consumer
    -0.61
     Fuj
    -0.61
    DonaldTrump
    -0.61
     Novel
    -0.59
     Yak
    -0.59
     Ake
    -0.59
     Paste
    -0.59
    POSITIVE LOGITS
    goers
    1.33
    yard
    1.19
    yards
    1.01
     bells
    0.98
    going
    0.97
     congregation
    0.95
     choir
    0.94
    helps
    0.93
     attendance
    0.93
    fires
    0.89
    Activations Density 0.032%

    No Known Activations