© 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. 0-RES-JB
    11. 15736
    Prev
    Next
    INDEX
    Explanations

    words related to Zen philosophy and culture

    oai_token-act-pair · gpt-3.5-turbo

    references to Zen, both as a concept and in various contexts

    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
     Hayden
    -0.78
     hail
    -0.77
     strand
    -0.73
    isSpecialOrderable
    -0.72
    umps
    -0.69
    indal
    -0.68
    Jamie
    -0.68
    CTV
    -0.67
    strings
    -0.67
     mashed
    -0.67
    POSITIVE LOGITS
     Zen
    3.75
    Zen
    3.00
     UX
    1.29
     Zy
    1.22
     Buddhism
    1.22
     Buddhist
    1.20
     Ryzen
    1.13
     Zar
    1.11
     Haku
    1.10
     Nietzsche
    1.09
    Activations Density 0.026%

    No Known Activations