© 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. 7-RES-JB
    11. 22975
    Prev
    Next
    INDEX
    Explanations

    names with the title "Rev" which is short for "Reverend"

    oai_token-act-pair · gpt-3.5-turbo

    references to religious figures or clergy, particularly those with the title "Rev."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holders
    -0.84
    女
    -0.66
    remlin
    -0.65
    matical
    -0.64
    bags
    -0.63
    ahime
    -0.63
    WAYS
    -0.63
     NIC
    -0.62
     stuffing
    -0.61
     combine
    -0.60
    POSITIVE LOGITS
    isions
    1.23
    olutions
    1.17
    olt
    1.05
    olver
    1.05
    olving
    1.03
    ision
    1.00
    ivals
    0.97
    olved
    0.96
    olves
    0.95
    atile
    0.92
    Activations Density 0.023%

    No Known Activations