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. 7-RES-JB
    6. 10507
    Prev
    Next
    INDEX
    Explanations

    specific dates or time-related events

    oai_token-act-pair · gpt-3.5-turbo

    references to current events and news-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Native
    -0.74
    apter
    -0.73
    $.
    -0.70
     Defendants
    -0.70
     foreclosure
    -0.69
     someday
    -0.67
     Plaintiff
    -0.67
    TOR
    -0.66
    Columb
    -0.64
    Years
    -0.64
    POSITIVE LOGITS
     apologised
    0.95
     criticised
    0.94
     spokesman
    0.93
     congratulated
    0.90
     meanwhile
    0.83
     reacted
    0.83
     angrily
    0.81
     spokeswoman
    0.80
     condem
    0.79
    iannopoulos
    0.77
    Activations Density 0.775%

    No Known Activations