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. 8610
    Prev
    Next
    INDEX
    Explanations

    texts related to various languages and characters that do not contribute to the meaning in English

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text

    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
    raints
    -0.91
    etsk
    -0.80
    ukong
    -0.73
    orship
    -0.71
    icter
    -0.69
    ensical
    -0.69
    nesday
    -0.69
    iflower
    -0.68
    conservancy
    -0.67
    orsche
    -0.66
    POSITIVE LOGITS
    ´
    0.91
    ¼
    0.89
    à¸
    0.89
    ãĥ£
    0.88
    à¦
    0.88
    ¡
    0.88
    ÙĬ
    0.88
    ng
    0.88
    ¬
    0.86
    Ð
    0.86
    Activations Density 0.007%

    No Known Activations