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. 8-RES-JB
    6. 7448
    Prev
    Next
    INDEX
    Explanations

    technical terms related to different fields such as technology, medical, and industrial processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific categories or measurements, especially in science, economics, and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    undrum
    -0.79
    mma
    -0.74
     Canaver
    -0.69
    rower
    -0.69
     Sorceress
    -0.67
    ilogy
    -0.65
     thanked
    -0.63
    agame
    -0.63
     Deadline
    -0.62
     congratulated
    -0.61
    POSITIVE LOGITS
     ones
    0.89
    aturdays
    0.76
    loads
    0.74
    abytes
    0.72
    bugs
    0.71
     clauses
    0.70
     commitments
    0.69
     lines
    0.68
     levels
    0.68
     bonuses
    0.68
    Activations Density 0.818%

    No Known Activations