© 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. 27896
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural elements within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.03
    1:0.02
    2:0.08
    3:0.07
    4:0.05
    5:0.04
    6:0.35
    7:0.05
    8:0.03
    9:0.07
    10:0.09
    11:0.07
    Negative Logits
     Tycoon
    -1.61
    ashtra
    -1.50
    ufact
    -1.49
    STER
    -1.45
    Kal
    -1.42
    inen
    -1.41
    ¯
    -1.37
    inki
    -1.36
    loo
    -1.35
    emouth
    -1.35
    POSITIVE LOGITS
     cc
    1.57
    ascript
    1.38
     Refresh
    1.33
    Spread
    1.33
    catentry
    1.28
     pp
    1.17
     speakers
    1.16
    speech
    1.15
     Entry
    1.15
     tick
    1.13
    Activations Density 0.001%

    No Known Activations