© 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. 6-RES-JB
    11. 2751
    Prev
    Next
    INDEX
    Explanations

    instructions or commands related to running programs or applications

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "run" and its variations in the context of executing programs or commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omical
    -0.86
    ault
    -0.75
    ideon
    -0.75
    ussen
    -0.69
    ighter
    -0.69
    ayers
    -0.69
    ippy
    -0.68
    imei
    -0.68
    orical
    -0.67
    cientious
    -0.67
    POSITIVE LOGITS
    tests
    0.86
    escape
    0.83
    ners
    0.79
    swick
    0.76
    NING
    0.75
     smoothly
    0.73
    times
    0.73
    tested
    0.71
     af
    0.70
    testing
    0.69
    Activations Density 0.042%

    No Known Activations