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. 8131
    Prev
    Next
    INDEX
    Explanations

    texts related to emergency calls and responses

    oai_token-act-pair · gpt-3.5-turbo

    references to communication technologies and notable figures in politics

    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
    arded
    -0.94
    arding
    -0.88
    ipolar
    -0.85
    uador
    -0.74
    orate
    -0.73
    overed
    -0.73
    aston
    -0.71
    judicial
    -0.71
    riet
    -0.69
    orders
    -0.69
    POSITIVE LOGITS
    Software
    0.82
    AAF
    0.81
    utra
    0.78
    Account
    0.77
    stice
    0.76
    XM
    0.75
    ustain
    0.75
    kaya
    0.74
    addle
    0.74
    ESSION
    0.74
    Activations Density 0.043%

    No Known Activations