Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 23856
    Prev
    Next
    INDEX
    Explanations

    the Unicode character "Ċ"

    oai_token-act-pair · gpt-3.5-turbo

    instances of high-stakes situations or events that involve danger or risk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hement
    -0.73
    ĸļ
    -0.71
    terday
    -0.69
     appe
    -0.69
    ushi
    -0.69
    utic
    -0.69
     instinct
    -0.68
    uly
    -0.68
    atis
    -0.68
    ails
    -0.66
    POSITIVE LOGITS
    SPONSORED
    0.99
    Newsletter
    0.96
    Advertisement
    0.91
    Article
    0.88
    Anonymous
    0.87
    However
    0.87
    Because
    0.86
    ³³³³³³³³³³³³³³³³
    0.86
    Recommended
    0.85
    Having
    0.85
    Activations Density 1.752%

    No Known Activations