© 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. 2-RES-JB
    11. 1515
    Prev
    Next
    INDEX
    Explanations

    coding-related terms, specifically focusing on the activation of the word "script."

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of scripts or scripting languages in code

    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
     Bears
    -0.75
    £ı
    -0.73
     Cheong
    -0.72
    iami
    -0.71
    ŃĶ
    -0.71
     Geh
    -0.69
     Admir
    -0.67
     Commodore
    -0.67
     Alto
    -0.65
     Barrett
    -0.65
    POSITIVE LOGITS
    script
    1.20
     scripting
    1.03
     script
    0.96
    ural
    0.93
    scripts
    0.93
     scripts
    0.92
    Pub
    0.86
    Deploy
    0.85
     Script
    0.83
     interpreter
    0.82
    Activations Density 0.010%

    No Known Activations