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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 15281
    Prev
    Next
    INDEX
    Explanations

    descriptions or symbols related to memorials or markers

    oai_token-act-pair · gpt-3.5-turbo

    references to commemorative events or memorials

    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
    ebook
    -0.94
    phasis
    -0.75
    advertisement
    -0.74
    SPONSORED
    -0.73
     Patreon
    -0.71
    Disclaimer
    -0.71
    Newsletter
    -0.71
    rils
    -0.71
    pour
    -0.69
    umbn
    -0.69
    POSITIVE LOGITS
     assassinated
    1.30
     martyr
    1.29
     slain
    1.24
     wartime
    1.23
     deceased
    1.19
     ancestors
    1.18
     WWII
    1.17
     ancestor
    1.17
     saints
    1.13
     1916
    1.13
    Activations Density 0.489%

    No Known Activations