© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 8675
    Prev
    Next
    INDEX
    Explanations

    questions or phrases involving evaluating or discussing significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.04
    2:0.05
    3:0.05
    4:0.11
    5:0.06
    6:0.05
    7:0.06
    8:0.04
    9:0.16
    10:0.04
    11:0.25
    Negative Logits
     mouths
    -2.68
     samples
    -2.48
     monitors
    -2.46
    payers
    -2.45
     pairs
    -2.44
    blers
    -2.39
     individuals
    -2.33
     traces
    -2.29
     heads
    -2.29
     largeDownload
    -2.28
    POSITIVE LOGITS
     stereotype
    2.66
     misconception
    2.48
    thing
    2.35
    osit
    2.27
    Myth
    2.27
     favourite
    2.21
     Favorite
    2.21
    Favorite
    2.20
     mantra
    2.15
    SQL
    2.14
    Activations Density 0.002%

    No Known Activations