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. 13092
    Prev
    Next
    INDEX
    Explanations

    sentences containing the word "seriously."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "seriously" used in various contexts

    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
    ifully
    -0.85
    tein
    -0.84
    anooga
    -0.75
     Thumbnails
    -0.74
    atu
    -0.73
    orem
    -0.70
     Tycoon
    -0.68
     Parenthood
    -0.67
    winner
    -0.67
    iful
    -0.67
    POSITIVE LOGITS
     entertained
    0.81
    minent
    0.77
     bothering
    0.76
    mond
    0.73
    jured
    0.73
    mun
    0.72
     dent
    0.72
    serious
    0.72
     retarded
    0.71
     injuring
    0.70
    Activations Density 0.017%

    No Known Activations