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. 19685
    Prev
    Next
    INDEX
    Explanations

    verbs related to boasting or expressing pride

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "brag" and related concepts

    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
     captcha
    -0.79
    ãĤ¡
    -0.74
    ãĥĥãĤ¯
    -0.70
    20439
    -0.68
    ãĥ¯ãĥ³
    -0.67
    ãĤ¨
    -0.67
    Ͻ
    -0.65
    ãĥĬ
    -0.64
    ictionary
    -0.63
    ãĤ»
    -0.63
    POSITIVE LOGITS
    doms
    0.97
    antly
    0.94
     loudly
    0.89
     confidently
    0.83
     boasted
    0.80
     bragging
    0.76
     about
    0.75
    ulate
    0.74
    acious
    0.74
     boasts
    0.72
    Activations Density 0.044%

    No Known Activations