© 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. 11-RES-JB
    11. 7749
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "according."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "according to" which indicates sourced information

    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
     eleph
    -0.90
     exting
    -0.83
    Þ
    -0.82
     occas
    -0.82
    ccording
    -0.77
    ailability
    -0.75
    ò
    -0.75
     helicop
    -0.75
    ñ
    -0.71
     tremend
    -0.70
    POSITIVE LOGITS
     to
    0.96
     TO
    0.63
     thereto
    0.61
    to
    0.60
    videos
    0.58
    %]
    0.55
    itely
    0.54
    Wiki
    0.53
     To
    0.53
    To
    0.53
    Activations Density 0.060%

    No Known Activations