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. 0-RES-JB
    6. 185
    Prev
    Next
    INDEX
    Explanations

    the word "Nor" followed by a word starting with a capital letter

    oai_token-act-pair · gpt-3.5-turbo

    the word "Nor" and variations of it, possibly indicating references to specific terms or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     casc
    -0.69
    uality
    -0.62
     dumped
    -0.61
     buffalo
    -0.61
     vectors
    -0.60
    xual
    -0.59
     heroes
    -0.58
     excited
    -0.58
     pee
    -0.57
    xc
    -0.56
    POSITIVE LOGITS
    Nor
    4.09
     Nor
    2.28
    nor
    1.94
    NOR
    1.43
     NOR
    1.37
     Norwegian
    1.34
     nor
    1.33
     Norway
    1.30
    Mor
    1.30
    Rather
    1.14
    Activations Density 0.019%

    No Known Activations