© 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. 6-RES-JB
    11. 10755
    Prev
    Next
    INDEX
    Explanations

    mentions of religious leaders with the title "Rev." in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to religious figures, specifically individuals with the title "Rev" (Reverend)

    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
    holders
    -0.80
    çĦ
    -0.71
    WAYS
    -0.68
    matical
    -0.67
    女
    -0.66
    remlin
    -0.66
     TOTAL
    -0.65
    wic
    -0.63
    bags
    -0.62
    matically
    -0.60
    POSITIVE LOGITS
    isions
    1.18
    olutions
    1.12
    olver
    1.03
    olt
    0.98
    ivals
    0.96
    olving
    0.95
    ision
    0.95
    olved
    0.94
    idence
    0.93
    atile
    0.93
    Activations Density 0.014%

    No Known Activations