© 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. 11-RES-JB
    11. 10227
    Prev
    Next
    INDEX
    Explanations

    software development-related terms, specifically focusing on programming languages and practices

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to programming, software development, and licensing issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     largeDownload
    -0.81
    ometown
    -0.75
    lah
    -0.74
    beck
    -0.74
     Photographer
    -0.74
    ulton
    -0.70
    ÄŁ
    -0.69
    ength
    -0.69
    aska
    -0.68
    lain
    -0.68
    POSITIVE LOGITS
     plugins
    1.57
     software
    1.55
     apps
    1.49
     APIs
    1.39
     applications
    1.38
     libraries
    1.38
     implementations
    1.36
     binaries
    1.36
     versions
    1.34
     programs
    1.32
    Activations Density 0.365%

    No Known Activations