© 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. 8-RES-JB
    11. 11337
    Prev
    Next
    INDEX
    Explanations

    commands involving running or compiling programs

    oai_token-act-pair · gpt-3.5-turbo

    commands related to executing programs and scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ylum
    -0.80
    omical
    -0.78
    ighter
    -0.70
    opol
    -0.69
    ayer
    -0.67
    iatus
    -0.66
    idal
    -0.63
    oxin
    -0.63
    bourg
    -0.63
    ayers
    -0.62
    POSITIVE LOGITS
    tests
    0.94
     GNU
    0.82
    linux
    0.77
    PDATE
    0.76
    times
    0.75
     tests
    0.75
    command
    0.74
    NING
    0.71
     commands
    0.71
     Tests
    0.71
    Activations Density 0.051%

    No Known Activations