© 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. 2-RES-JB
    11. 8940
    Prev
    Next
    INDEX
    Explanations

    code syntax involving logical operators and conditional statements

    oai_token-act-pair · gpt-3.5-turbo

    logical operators and syntax elements commonly used in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.80
    ulative
    -0.80
    ulation
    -0.80
    itives
    -0.78
    arnaev
    -0.74
    ulated
    -0.73
    ulates
    -0.73
    hof
    -0.72
    apers
    -0.72
    omers
    -0.71
    POSITIVE LOGITS
     [];
    1.01
    ||||
    1.00
     ||
    0.98
    avascript
    0.82
    ··
    0.75
     !
    0.71
    ||
    0.69
     curry
    0.66
     Koran
    0.65
     something
    0.64
    Activations Density 0.006%

    No Known Activations