© 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. 6-RES-JB
    11. 8530
    Prev
    Next
    INDEX
    Explanations

    words related to religious offenses, particularly blasphemy, and places like monasteries or convents

    oai_token-act-pair · gpt-3.5-turbo

    references to religious controversy and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ative
    -0.85
    ratulations
    -0.77
    pill
    -0.76
    ordial
    -0.75
    tarians
    -0.70
    ota
    -0.70
     contribut
    -0.70
    atched
    -0.68
    tails
    -0.68
    yll
    -0.68
    POSITIVE LOGITS
     laureate
    0.80
    clair
    0.79
     convict
    0.78
    iscopal
    0.76
     confinement
    0.76
     Parables
    0.76
     nuns
    0.75
     blasp
    0.74
     Cells
    0.72
     Parish
    0.70
    Activations Density 0.094%

    No Known Activations