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. 11-RES-JB
    6. 8404
    Prev
    Next
    INDEX
    Explanations

    references to specific points in time or instances of events happening

    oai_token-act-pair · gpt-3.5-turbo

    mentions of significant historical events or milestones

    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
    ords
    -0.65
     meantime
    -0.64
     ILCS
    -0.63
     Attribution
    -0.57
     Extension
    -0.56
     Journals
    -0.56
     abound
    -0.55
    olor
    -0.54
    modules
    -0.54
     priceless
    -0.54
    POSITIVE LOGITS
     ever
    1.28
     EVER
    1.26
     ventured
    1.12
     interacted
    1.12
     bothered
    1.07
    ever
    1.03
     visited
    1.01
     interfered
    1.00
     encountered
    0.96
     dared
    0.96
    Activations Density 0.133%

    No Known Activations