© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 22495
    Prev
    Next
    INDEX
    Explanations

    mentions of the occupation "pastor"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "pastor."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yx
    -0.66
     Gadget
    -0.66
     Interface
    -0.65
    competitive
    -0.64
    play
    -0.64
    Balance
    -0.63
     symm
    -0.63
    alysis
    -0.62
     Emerald
    -0.62
    çĶ
    -0.61
    POSITIVE LOGITS
     pastor
    3.81
     Pastor
    3.01
     pastors
    2.58
     preacher
    2.28
     rabbi
    1.98
     bishop
    1.72
     Reverend
    1.65
     sermon
    1.65
     parish
    1.56
     theolog
    1.52
    Activations Density 0.014%

    No Known Activations