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. 8979
    Prev
    Next
    INDEX
    Explanations

    adverbs that end with 'ingly'

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that convey a sense of disappointment or negativity

    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
     Mon
    -0.60
     mov
    -0.56
     LCS
    -0.56
     div
    -0.55
     replacing
    -0.55
     )]
    -0.54
     var
    -0.53
     Main
    -0.53
     form
    -0.52
     Wed
    -0.51
    POSITIVE LOGITS
    ingly
    5.03
    ously
    1.61
    ively
    1.60
    ably
    1.60
    ishly
    1.56
    edly
    1.50
    fully
    1.47
    ibly
    1.46
    lessly
    1.39
    ings
    1.31
    Activations Density 0.014%

    No Known Activations