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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21252
    Prev
    Next
    INDEX
    Explanations

    references to specific religious groups, particularly Orthodox

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Orthodox" in various contexts related to Orthodox Judaism and Christianity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptives
    -0.90
    ptoms
    -0.89
    nels
    -0.82
    arcity
    -0.78
    stract
    -0.77
    ************
    -0.76
    rill
    -0.73
    uncle
    -0.70
    aneously
    -0.70
    enance
    -0.70
    POSITIVE LOGITS
    omy
    0.90
     rabb
    0.84
    osate
    0.83
    thodox
    0.80
    onite
    0.80
    y
    0.80
     Patriarch
    0.79
     fundamental
    0.78
     Judaism
    0.77
     orthodox
    0.76
    Activations Density 0.016%

    No Known Activations