© 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. 1-RES-JB
    11. 14142
    Prev
    Next
    INDEX
    Explanations

    mentions of the programming language Lisp

    oai_token-act-pair · gpt-3.5-turbo

    references to the programming language Lisp and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rating
    -0.79
    hin
    -0.78
    eous
    -0.76
    awei
    -0.74
    ometown
    -0.71
    anmar
    -0.69
    obbies
    -0.67
    hemy
    -0.66
    ortium
    -0.66
     Gaia
    -0.65
    POSITIVE LOGITS
     Lisp
    1.04
     Clojure
    0.84
    mers
    0.81
    Lua
    0.78
    Script
    0.77
     Haskell
    0.76
     mosqu
    0.74
    BSD
    0.73
     Emacs
    0.72
     Scala
    0.71
    Activations Density 0.020%

    No Known Activations