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. 2-RES-JB
    6. 17956
    Prev
    Next
    INDEX
    Explanations

    words related to memorabilia and memory

    oai_token-act-pair · gpt-3.5-turbo

    references to memory and memorization

    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
    OPLE
    -0.73
    IRO
    -0.70
     Silk
    -0.67
     Empires
    -0.63
    WP
    -0.62
     Syrians
    -0.61
     Citizens
    -0.61
     ACS
    -0.60
    Conclusion
    -0.60
    Merit
    -0.60
    POSITIVE LOGITS
    abilia
    1.60
     memor
    1.32
    ably
    1.03
    ographed
    0.98
    etically
    0.95
    ific
    0.95
    ruction
    0.91
    andum
    0.87
    brance
    0.87
    istically
    0.87
    Activations Density 0.008%

    No Known Activations