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. 10-RES-JB
    6. 16746
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences where "by far" is used to emphasize a superlative or strong comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing extreme comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emis
    -0.77
    osponsors
    -0.72
    mare
    -0.69
    ysis
    -0.68
    cffff
    -0.67
    ools
    -0.65
    ibilities
    -0.65
     Eggs
    -0.61
    kefeller
    -0.60
    anamo
    -0.60
    POSITIVE LOGITS
     superior
    0.69
     outnumbered
    0.66
     preferable
    0.65
     my
    0.60
     outweigh
    0.60
     âĸº
    0.59
     louder
    0.59
     outwe
    0.57
     preferring
    0.56
     exceeded
    0.56
    Activations Density 0.027%

    No Known Activations