Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8041
    Prev
    Next
    INDEX
    Explanations

    every instance of the word "exactly"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "exactly" to emphasize precision or specificity in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ker
    -0.80
    rug
    -0.77
    rift
    -0.76
    olyn
    -0.73
     sacrific
    -0.65
    asta
    -0.64
    kers
    -0.64
    cler
    -0.63
    gers
    -0.63
    isson
    -0.63
    POSITIVE LOGITS
     opposite
    0.74
    ãĤ¨
    0.73
     wrong
    0.72
    ãĥ´ãĤ¡
    0.67
     aligned
    0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.65
    æ©Ł
    0.65
     suited
    0.63
    ÃĽ
    0.63
     tuned
    0.62
    Activations Density 0.014%

    No Known Activations