© 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. 1-RES-JB
    11. 21128
    Prev
    Next
    INDEX
    Explanations

    religious contexts and terms

    oai_token-act-pair · gpt-3.5-turbo

    references to religion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HAEL
    -0.79
    berry
    -0.75
    0000000000000000
    -0.71
    berries
    -0.69
    ãģ¦
    -0.68
    displayText
    -0.67
    enegger
    -0.65
    ãģ®ç
    -0.64
    ãĥ¼ãĥĨãĤ£
    -0.62
     Wilde
    -0.62
    POSITIVE LOGITS
    igion
    1.21
    igious
    1.16
    iance
    1.08
    iability
    0.91
    ient
    0.90
    icity
    0.90
    iable
    0.89
     Rel
    0.87
    atives
    0.87
    atively
    0.86
    Activations Density 0.007%

    No Known Activations