Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 89
    Prev
    Next
    INDEX
    Explanations

    programming code related terms

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and syntax related to programming or coding structures

    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
    tumblr
    -1.12
    âĹ¼
    -0.86
    raq
    -0.85
    qus
    -0.80
    quickShipAvailable
    -0.79
    icut
    -0.78
    MpServer
    -0.77
    avery
    -0.76
    ousy
    -0.76
    ocaust
    -0.76
    POSITIVE LOGITS
    ){
    0.99
     args
    0.87
     );
    0.84
    );
    0.82
     ())
    0.79
     )
    0.78
     init
    0.75
     })
    0.73
    ):
    0.72
     {}
    0.72
    Activations Density 0.088%

    No Known Activations