© 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 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. 3-RES-JB
    11. 11586
    Prev
    Next
    INDEX
    Explanations

    words related to authority or pontification

    oai_token-act-pair · gpt-3.5-turbo

    terms related to church authority or religious leadership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dynamics
    -0.82
     Oil
    -0.79
     Sabha
    -0.78
     Door
    -0.77
     Shack
    -0.77
    Brand
    -0.74
    nergy
    -0.73
     Price
    -0.73
     Royale
    -0.73
     Weaver
    -0.72
    POSITIVE LOGITS
    haps
    0.89
    itted
    0.87
     pont
    0.87
    uss
    0.86
    oled
    0.83
     jour
    0.80
     pier
    0.75
    icular
    0.75
    anging
    0.74
     parach
    0.74
    Activations Density 0.013%

    No Known Activations