© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3094
    Prev
    Next
    INDEX
    Explanations

    terms related to the colonization of biblical interpretation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to theological interpretation and biblical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    naire
    -0.98
    76561
    -0.96
    netflix
    -0.96
    daq
    -0.84
     Indust
    -0.83
     cort
    -0.83
    ratom
    -0.81
     rink
    -0.77
    AMI
    -0.77
    iband
    -0.76
    POSITIVE LOGITS
     biblical
    1.85
     Scripture
    1.82
     Bible
    1.81
     Biblical
    1.79
     scripture
    1.69
     Scriptures
    1.68
    iblical
    1.66
     scriptures
    1.54
     Psal
    1.52
     verses
    1.51
    Activations Density 0.288%

    No Known Activations