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. 2-RES-JB
    6. 10941
    Prev
    Next
    INDEX
    Explanations

    religious or spiritual references and teachings

    oai_token-act-pair · gpt-3.5-turbo

    themes and references related to religious hope and forgiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taboola
    -0.93
    sbm
    -0.80
     actionGroup
    -0.77
    CTV
    -0.73
    UGC
    -0.70
    thumbnails
    -0.68
    ovember
    -0.68
     CV
    -0.68
     trending
    -0.68
    Indust
    -0.67
    POSITIVE LOGITS
     divine
    0.99
     Divine
    0.92
     Buddha
    0.92
     unto
    0.91
     blessings
    0.90
     consec
    0.90
     Zoro
    0.90
     deity
    0.89
     mystic
    0.87
     Apostles
    0.87
    Activations Density 0.671%

    No Known Activations