© 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. 9-ATT-KK
    11. 934
    Prev
    Next
    INDEX
    Explanations

    conversational phrases and informal expressions

    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
    0:0.06
    1:0.02
    2:0.08
    3:0.31
    4:0.05
    5:0.06
    6:0.05
    7:0.09
    8:0.06
    9:0.04
    10:0.07
    11:0.07
    Negative Logits
     ­
    -3.73
    ­
    -2.55
    �
    -2.50
     �
    -2.38
    ​
    -2.33
    ‑
    -2.21
    ​​
    -2.19
     Combined
    -2.16
     Associated
    -2.14
    ‐
    -2.13
    POSITIVE LOGITS
     shit
    2.66
     alot
    2.63
     crap
    2.62
     fucked
    2.60
     fuck
    2.57
    ulhu
    2.54
     ;)
    2.54
    fuck
    2.52
     didnt
    2.51
     cunt
    2.49
    Activations Density 2.463%

    No Known Activations