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

    Neuronpedia

    Jacobian LensNEW
    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. 15007
    Prev
    Next
    INDEX
    Explanations

    references to news agencies or press outlets

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Associated Press

    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
    arily
    -0.68
     imm
    -0.63
     underpin
    -0.61
    lessly
    -0.60
     dissolved
    -0.58
     rainbow
    -0.56
    gone
    -0.56
     horr
    -0.56
    peror
    -0.56
     sucker
    -0.55
    POSITIVE LOGITS
     Press
    1.39
     Newsp
    1.02
     Journals
    1.01
     PRESS
    0.93
     States
    0.79
    âĢ¦)
    0.76
     Nations
    0.76
     Franch
    0.76
     Journalists
    0.74
    Press
    0.74
    Activations Density 0.023%

    No Known Activations