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. 1-RES-JB
    6. 17803
    Prev
    Next
    INDEX
    Explanations

    keywords related to a specific abbreviation, "NS" (with various numerical suffixes) and a few instances of "CIS"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations or entities, particularly those abbreviated as "NS" or "CIS."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĸ¬âĸ¬
    -0.82
    about
    -0.73
    icago
    -0.70
    heit
    -0.69
    ously
    -0.69
    oise
    -0.68
    iences
    -0.68
    iens
    -0.68
    debian
    -0.66
    bugs
    -0.66
    POSITIVE LOGITS
     NS
    1.16
    FW
    1.04
     ns
    0.83
    IJ
    0.80
    BM
    0.78
    AAF
    0.78
     concess
    0.76
    FG
    0.75
    NN
    0.74
    NS
    0.73
    Activations Density 0.004%

    No Known Activations