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. 4-RES-JB
    6. 12773
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce or emphasize a list of items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to various subjects and topics denoted by "the" followed by descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SOM
    -0.75
    ANE
    -0.67
    ahn
    -0.65
     Reincarn
    -0.64
    fulness
    -0.63
     anew
    -0.62
     Tsukuyomi
    -0.62
     Chapel
    -0.62
    bye
    -0.60
     Archdemon
    -0.60
    POSITIVE LOGITS
    oké
    0.74
    phabet
    0.74
    iler
    0.70
    oples
    0.70
    acan
    0.68
    erville
    0.68
    ilic
    0.67
    upper
    0.67
    eligible
    0.67
    visual
    0.66
    Activations Density 0.097%

    No Known Activations