© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 17342
    Prev
    Next
    INDEX
    Explanations

    code snippets related to defining functions and handling errors

    oai_token-act-pair · gpt-3.5-turbo

    function declarations and their parameters in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MSN
    -0.90
    soDeliveryDate
    -0.77
    TPP
    -0.74
     Shutterstock
    -0.73
    prising
    -0.73
    ebook
    -0.68
    Sov
    -0.66
    æĪ¦
    -0.65
    assic
    -0.64
    bos
    -0.62
    POSITIVE LOGITS
     {
    1.27
     {}
    1.13
    {
    1.02
    {"
    0.94
    ){
    0.94
     override
    0.92
     throws
    0.89
    :{
    0.88
     {\
    0.84
     {:
    0.81
    Activations Density 0.040%

    No Known Activations