© 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 EvalsExportsinterp-engineNEWAPI 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. 11419
    Prev
    Next
    INDEX
    Explanations

    web URLs with specific patterns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of HTML or programming code syntax

    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
     vacuum
    -0.63
     Penguin
    -0.61
     populated
    -0.59
     Poles
    -0.58
    ipel
    -0.57
     unlimited
    -0.56
     Polish
    -0.56
     Labrador
    -0.55
     ...
    -0.55
     shock
    -0.55
    POSITIVE LOGITS
    //
    3.26
    ///
    1.88
    /*
    1.88
    /**
    1.77
    ////
    1.69
    ////////////////
    1.33
    */
    1.25
    /
    1.24
    ////////
    1.24
    /,
    1.23
    Activations Density 0.004%

    No Known Activations