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. 4-RES-JB
    6. 3892
    Prev
    Next
    INDEX
    Explanations

    patterns of characters that are non-English text mixed with symbols and numbers

    oai_token-act-pair · gpt-3.5-turbo

    characters and numerals in various languages and scripts

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

    No Comments

    Negative Logits
    haps
    -0.81
    matically
    -0.79
    ngth
    -0.79
    ippi
    -0.77
    meal
    -0.74
    Else
    -0.73
     myster
    -0.72
     Skydragon
    -0.71
    asus
    -0.71
    avers
    -0.70
    POSITIVE LOGITS
    ÙĬ
    0.88
    Ñĥ
    0.85
    ب
    0.82
    ãĥ¼
    0.82
    ÙĪ
    0.81
    س
    0.79
    rican
    0.78
    ãĥ¥
    0.78
    ׾
    0.77
    rique
    0.77
    Activations Density 0.005%

    No Known Activations