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. 10-RES-JB
    6. 20172
    Prev
    Next
    INDEX
    Explanations

    technology-related terms and company names

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to technology and media organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oÄŁan
    -0.83
    ances
    -0.79
    Previous
    -0.78
    rawdownloadcloneembedreportprint
    -0.76
    atari
    -0.75
    "]=>
    -0.74
    yers
    -0.72
    quist
    -0.72
    enz
    -0.72
    ance
    -0.70
    POSITIVE LOGITS
     namely
    1.35
     dubbed
    1.05
     aptly
    1.00
     called
    0.99
     albeit
    0.95
     Spectre
    0.93
     which
    0.93
     titled
    0.91
     nicknamed
    0.89
     entitled
    0.85
    Activations Density 0.195%

    No Known Activations