© 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. 4-RES-JB
    11. 10212
    Prev
    Next
    INDEX
    Explanations

    commands or instructions in computer programming contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of commands and instructions related to software installation and programming

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

    No Comments

    Negative Logits
    midt
    -0.74
     Flavoring
    -0.71
    ONSORED
    -0.69
    YL
    -0.68
     Investor
    -0.68
    abies
    -0.68
     Democr
    -0.66
    aucus
    -0.66
    CLASSIFIED
    -0.66
     Boys
    -0.65
    POSITIVE LOGITS
     commands
    1.10
    eering
    0.97
     cmd
    0.93
     command
    0.91
    stration
    0.90
    naire
    0.83
    command
    0.81
     prompt
    0.80
     injection
    0.79
     sender
    0.79
    Activations Density 0.009%

    No Known Activations