© 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
    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. 6429
    Prev
    Next
    INDEX
    Explanations

    repetitive mentions of a specific news channel

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Fox News."

    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
    chest
    -0.72
    yip
    -0.68
    utical
    -0.67
    ãĤ¨ãĥ«
    -0.67
    rette
    -0.66
    ause
    -0.66
    BuyableInstoreAndOnline
    -0.65
    vol
    -0.65
    isu
    -0.65
     awe
    -0.64
    POSITIVE LOGITS
     Channel
    1.33
    '
    1.04
     anchor
    0.88
     Network
    0.87
     Anch
    0.87
    radio
    0.86
     correspondent
    0.85
    Radio
    0.84
     contributor
    0.84
     Latino
    0.83
    Activations Density 0.041%

    No Known Activations