Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 19922
    Prev
    Next
    INDEX
    Explanations

    references to religious figures, particularly bishops

    oai_token-act-pair · gpt-3.5-turbo

    references to religious figures and positions within the church hierarchy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pak
    -0.69
     Wonderland
    -0.66
    BAT
    -0.63
     Recovery
    -0.63
     NP
    -0.63
    TOR
    -0.59
     Asgard
    -0.59
     Pipeline
    -0.59
     Agency
    -0.59
     Coverage
    -0.58
    POSITIVE LOGITS
    esses
    1.25
    bishop
    1.19
     priests
    1.17
     priest
    1.17
    ess
    1.16
     bishop
    1.16
    ric
    1.13
    ocese
    1.13
     ordained
    1.13
     Archbishop
    1.12
    Activations Density 0.074%

    No Known Activations