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. 5678
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms containing "NS"

    oai_token-act-pair · gpt-3.5-turbo

    the acronym "NS" and its variants related to various contexts in the document

    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
     ra
    -0.63
    irgin
    -0.60
     doub
    -0.59
     failing
    -0.57
     Mile
    -0.57
     techno
    -0.57
     tidy
    -0.57
     Horse
    -0.56
     caution
    -0.56
     empty
    -0.56
    POSITIVE LOGITS
    FW
    1.23
    NS
    1.22
    fw
    1.07
    ertodd
    1.04
    ESSION
    0.91
    erves
    0.91
    HT
    0.90
    ettings
    0.88
    erve
    0.88
    emonic
    0.83
    Activations Density 0.004%

    No Known Activations