© 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. 8338
    Prev
    Next
    INDEX
    Explanations

    references to the programming language Perl

    oai_token-act-pair · gpt-3.5-turbo

    references to programming languages, particularly Perl, and specific geographic locations, such as Perth and Peru

    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
    isSpecialOrderable
    -0.84
    Cy
    -0.75
    γ
    -0.75
    LCS
    -0.73
    GT
    -0.70
    uge
    -0.69
    cy
    -0.68
     brunch
    -0.67
    KK
    -0.67
    Ze
    -0.67
    POSITIVE LOGITS
     Perth
    2.35
     Perl
    2.12
     Peru
    1.85
     PER
    1.58
     Lima
    1.54
     perl
    1.54
     Prest
    1.50
    Per
    1.40
     Per
    1.37
     Perse
    1.22
    Activations Density 0.026%

    No Known Activations