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. 20937
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Shar" followed by a number (e.g., Shar9, Shar10)

    oai_token-act-pair · gpt-3.5-turbo

    references to Sharia law and related legal systems

    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
    ĸļ
    -0.73
     Europa
    -0.71
    ortium
    -0.71
     Dangerous
    -0.69
    vironment
    -0.66
     Hawaiian
    -0.65
    ALS
    -0.64
     Uran
    -0.63
    é¾įå¥ij士
    -0.63
    ATS
    -0.62
    POSITIVE LOGITS
    pton
    1.12
    ples
    1.07
    ãĥ£
    1.06
    pling
    0.99
    pless
    0.98
    ning
    0.93
    quet
    0.90
    jah
    0.88
    pering
    0.86
    pen
    0.85
    Activations Density 0.010%

    No Known Activations