© 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. 0-RES-JB
    11. 13615
    Prev
    Next
    INDEX
    Explanations

    terms related to principles, prudence, and strategy

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "prince" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cobb
    -0.70
     Flake
    -0.64
     botched
    -0.64
     Uk
    -0.63
     intercepted
    -0.63
     blues
    -0.59
     transitions
    -0.59
     Zamb
    -0.59
     disabling
    -0.59
     Aber
    -0.58
    POSITIVE LOGITS
    pr
    4.30
    Pr
    1.89
    prising
    1.47
    PR
    1.47
    pri
    1.43
     Pr
    1.41
     pr
    1.35
     prin
    1.34
    prises
    1.29
    spr
    1.28
    Activations Density 0.006%

    No Known Activations