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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 9588
    Prev
    Next
    INDEX
    Explanations

    terms related to the consequences and impacts of various events or actions

    oai_token-act-pair · gpt-3.5-turbo

    topics related to adverse effects and crises affecting various sectors or populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wanted
    -0.77
    irlf
    -0.74
    utenant
    -0.69
    apest
    -0.64
    IBLE
    -0.64
    VALUE
    -0.63
    wark
    -0.63
    soDeliveryDate
    -0.62
    dds
    -0.61
     hopes
    -0.61
    POSITIVE LOGITS
     interventions
    1.09
     Recession
    1.01
     inaction
    0.99
     intervention
    0.95
     policies
    0.94
     globalization
    0.94
     recession
    0.93
     influx
    0.92
     downturn
    0.92
     onslaught
    0.90
    Activations Density 0.383%

    No Known Activations