© 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. 23546
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming languages, specifically focusing on Haskell and Perl

    oai_token-act-pair · gpt-3.5-turbo

    references to programming languages, particularly Haskell and Perl

    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
    hest
    -0.85
     Rockefeller
    -0.80
    oples
    -0.78
    ablishment
    -0.75
    abouts
    -0.75
    hin
    -0.72
    rha
    -0.71
    HAEL
    -0.71
    lain
    -0.71
    ellen
    -0.70
    POSITIVE LOGITS
    Script
    1.00
     bindings
    0.92
     interpreter
    0.92
    API
    0.88
     syntax
    0.87
     Libraries
    0.85
     runtime
    0.82
    SourceFile
    0.82
     implementations
    0.82
     libraries
    0.82
    Activations Density 0.043%

    No Known Activations