© 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. 3033
    Prev
    Next
    INDEX
    Explanations

    references to the news channel "Fox News"

    oai_token-act-pair · gpt-3.5-turbo

    references to Fox News

    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
    chest
    -0.74
    isu
    -0.71
    actionDate
    -0.64
    nee
    -0.63
     sheet
    -0.63
    ffect
    -0.62
    ause
    -0.62
    album
    -0.61
    knife
    -0.61
    utical
    -0.60
    POSITIVE LOGITS
     Channel
    1.25
    '
    0.99
    Radio
    0.88
     Tonight
    0.88
     Anch
    0.87
     Belief
    0.86
     pund
    0.84
     Radio
    0.83
     anchor
    0.83
     commentator
    0.80
    Activations Density 0.037%

    No Known Activations