© 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. 5-ATT-KK
    11. 42502
    Prev
    Next
    INDEX
    Explanations

    text structures or elements related to emphasis and punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.17
    1:0.06
    2:0.04
    3:0.07
    4:0.04
    5:0.07
    6:0.04
    7:0.04
    8:0.27
    9:0.07
    10:0.04
    11:0.05
    Negative Logits
     seiz
    -2.02
    tein
    -1.93
    ktop
    -1.80
     arrang
    -1.77
    lement
    -1.73
     cous
    -1.72
     tranqu
    -1.68
    mob
    -1.65
    ettel
    -1.64
    etimes
    -1.62
    POSITIVE LOGITS
     Associates
    1.76
    Second
    1.66
     Sample
    1.58
     Pants
    1.54
     Specific
    1.52
     Picture
    1.50
    )=(
    1.50
     Biden
    1.49
     42
    1.48
     Second
    1.47
    Activations Density 0.007%

    No Known Activations