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. 15615
    Prev
    Next
    INDEX
    Explanations

    text related to computer programming, especially involving functions, variables, and data manipulation

    oai_token-act-pair · gpt-3.5-turbo

    elements related to data structure and database operations

    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
     bluff
    -0.71
     electing
    -0.67
     thr
    -0.65
     plung
    -0.64
     fer
    -0.63
     gig
    -0.61
     accrued
    -0.61
     Cele
    -0.60
     shielding
    -0.60
     avalanche
    -0.60
    POSITIVE LOGITS
    ().
    1.26
    cdn
    1.11
    ();
    1.03
    ())
    1.02
    ({
    1.02
    #$
    0.97
    ()
    0.94
    (),
    0.93
    ());
    0.93
    ignore
    0.92
    Activations Density 0.094%

    No Known Activations