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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14948
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating rankings and frequencies

    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
    1:0.24
    2:0.04
    3:0.07
    4:0.09
    5:0.03
    6:0.05
    7:0.15
    8:0.07
    9:0.06
    10:0.05
    11:0.07
    Negative Logits
     substitute
    -2.68
    obal
    -2.58
     Matte
    -2.37
     enhancements
    -2.22
    bad
    -2.20
     Enhance
    -2.20
     Sour
    -2.19
     herbal
    -2.18
     placeholder
    -2.15
     sour
    -2.13
    POSITIVE LOGITS
     Highest
    3.89
    most
    3.80
    highest
    3.66
    est
    3.50
    iest
    3.45
    Hig
    3.45
    liest
    3.31
     Worst
    3.17
     youngest
    3.07
    largest
    3.04
    Activations Density 0.033%

    No Known Activations