© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 9803
    Prev
    Next
    INDEX
    Explanations

    references to specific doctrines or beliefs, such as "Doctrine and Covenants", "Von Haessler Doctrine", and "Positive Thinking Doctrine."

    oai_token-act-pair · gpt-3.5-turbo

    references to religious or philosophical doctrines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rers
    -0.96
    PsyNetMessage
    -0.92
     Gork
    -0.89
    elling
    -0.83
    ulates
    -0.79
    rer
    -0.78
    kees
    -0.77
    alien
    -0.76
    athe
    -0.76
    ELL
    -0.75
    POSITIVE LOGITS
     revelation
    0.69
     belief
    0.67
     discharge
    0.67
     pronounce
    0.67
     doctrine
    0.66
     slew
    0.66
     deeds
    0.65
     Doctrine
    0.63
     disclaim
    0.62
     tune
    0.62
    Activations Density 0.088%

    No Known Activations