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

    Neuronpedia

    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. 9-ATT-KK
    11. 21274
    Prev
    Next
    INDEX
    Explanations

    phrases indicating strong emotional reactions or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.03
    2:0.05
    3:0.04
    4:0.04
    5:0.04
    6:0.20
    7:0.05
    8:0.06
    9:0.28
    10:0.03
    11:0.04
    Negative Logits
     whale
    -3.91
     Whale
    -3.80
     Kodi
    -3.74
    untu
    -3.64
     Ubuntu
    -3.39
    kernel
    -3.37
     Lily
    -3.29
     tsun
    -3.23
     DISTR
    -3.22
    tan
    -3.21
    POSITIVE LOGITS
     Jacobs
    10.46
    Jac
    8.08
     Jac
    6.10
    jac
    5.25
     Jacob
    4.64
     Cohn
    4.51
    Jacob
    4.33
     IB
    4.12
    Brook
    4.07
    Jackson
    3.70
    Activations Density 0.002%

    No Known Activations