© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 16098
    Prev
    Next
    INDEX
    Explanations

    news outlets or media sources

    oai_token-act-pair · gpt-3.5-turbo

    references to specific news organizations or media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¯
    -0.76
     privile
    -0.72
    album
    -0.66
    backs
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
    abiding
    -0.65
     haunted
    -0.64
     registers
    -0.62
    etting
    -0.62
     doomed
    -0.61
    POSITIVE LOGITS
    News
    1.26
     News
    1.24
    news
    0.95
     Politics
    0.93
    Sport
    0.88
    Politics
    0.88
    NEWS
    0.88
     Radio
    0.87
    Sports
    0.87
     Television
    0.86
    Activations Density 0.075%

    No Known Activations