© 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. 21079
    Prev
    Next
    INDEX
    Explanations

    textual formatting and numerical data within the document

    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
    0:0.03
    1:0.51
    2:0.03
    3:0.04
    4:0.03
    5:0.06
    6:0.04
    7:0.03
    8:0.02
    9:0.07
    10:0.03
    11:0.05
    Negative Logits
     effortlessly
    -2.71
     Farrell
    -2.57
    omin
    -2.55
     denomin
    -2.54
    ered
    -2.49
    itu
    -2.45
     disreg
    -2.45
    373
    -2.44
     fundamentally
    -2.38
    aneously
    -2.37
    POSITIVE LOGITS
    15
    4.51
     15
    4.32
    16
    4.21
     16
    4.09
    14
    3.85
     14
    3.73
    815
    3.62
    Afee
    3.34
    150
    3.30
     1500
    3.26
    Activations Density 0.028%

    No Known Activations