© 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. 0-RES-JB
    11. 13300
    Prev
    Next
    INDEX
    Explanations

    phrases related to computer programming or technical processes, particularly focusing on the concept of code execution and related operations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "execution" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qua
    -0.75
    gger
    -0.74
    taboola
    -0.71
    cot
    -0.70
    bi
    -0.67
    rain
    -0.67
     Eps
    -0.66
    女
    -0.64
     Ner
    -0.64
     Roz
    -0.63
    POSITIVE LOGITS
     execution
    4.06
     executions
    2.86
     Execution
    2.75
     executed
    2.43
     executing
    2.37
     execute
    2.22
     executes
    2.00
    Exec
    1.85
     Exec
    1.59
    exec
    1.55
    Activations Density 0.006%

    No Known Activations