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. 19704
    Prev
    Next
    INDEX
    Explanations

    words related to technical features or functions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce or reference specific attributes or functions associated with items

    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
    ourcing
    -0.74
    ODY
    -0.71
    etheless
    -0.66
    igated
    -0.65
    icipated
    -0.64
    artisan
    -0.61
    rafted
    -0.61
    ION
    -0.61
    oubted
    -0.60
    aukee
    -0.60
    POSITIVE LOGITS
     accompanies
    1.39
     governs
    1.39
     allows
    1.36
     regulates
    1.34
     attaches
    1.33
     directs
    1.31
     activates
    1.30
     determines
    1.29
     enables
    1.29
     lets
    1.28
    Activations Density 0.165%

    No Known Activations