© 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 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. 497
    Prev
    Next
    INDEX
    Explanations

    commands or instructions in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    the word "command" as it appears in the context of computer commands or programming instructions

    oai_token-act-pair · gpt-4-turbo

    instructions related to command-line operations

    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
     Democr
    -0.73
     Flavoring
    -0.68
     Boys
    -0.62
    ItemTracker
    -0.61
    430
    -0.61
     Chomsky
    -0.61
    bid
    -0.60
     Gund
    -0.60
     CFR
    -0.60
    Versions
    -0.59
    POSITIVE LOGITS
    eering
    1.24
     commands
    1.06
    eers
    1.00
     command
    0.96
    eer
    0.88
    command
    0.87
     commanded
    0.83
    naire
    0.83
     Commands
    0.78
    Command
    0.77
    Activations Density 0.011%

    No Known Activations