© 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. 8-RES-JB
    11. 9986
    Prev
    Next
    INDEX
    Explanations

    command line instructions and technical terms related to computer programming

    oai_token-act-pair · gpt-3.5-turbo

    technical terminology related to software installation and error messages

    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
    •single token firings
    Fires individually on "docker", " json", " docker", " ssh", " python", ...

    No Comments

    Negative Logits
     Ninth
    -0.93
     Kahn
    -0.86
     Ear
    -0.83
     Pai
    -0.82
     Ending
    -0.81
     Noel
    -0.80
     Rarity
    -0.80
     Tenth
    -0.79
     HIP
    -0.78
     Marks
    -0.77
    POSITIVE LOGITS
    utils
    1.39
    ctl
    1.25
    cli
    1.18
    client
    1.17
    plugin
    1.17
    tools
    1.14
    rc
    1.13
    info
    1.11
    proxy
    1.10
    config
    1.09
    Activations Density 0.251%

    No Known Activations