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. 15531
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or appearances happening at specific places

    oai_token-act-pair · gpt-3.5-turbo

    references to specific events and their timings

    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
    xual
    -0.74
    irez
    -0.72
     steered
    -0.72
    /(
    -0.68
     drilled
    -0.66
     guessed
    -0.66
     reliant
    -0.64
    existent
    -0.62
    gered
    -0.62
     benefited
    -0.60
    POSITIVE LOGITS
     CES
    1.19
     SX
    1.16
    rium
    1.05
     PAX
    1.01
     Comic
    1.00
     Cannes
    0.96
     RTX
    0.95
     Wrestle
    0.95
     festivals
    0.93
     Blizz
    0.89
    Activations Density 0.109%

    No Known Activations