© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 13901
    Prev
    Next
    INDEX
    Explanations

    elements related to statistics and numerical data

    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
    0:0.02
    1:0.57
    2:0.02
    3:0.04
    4:0.02
    5:0.05
    6:0.05
    7:0.02
    8:0.02
    9:0.06
    10:0.03
    11:0.04
    Negative Logits
    �
    -2.65
    ythm
    -2.63
    ブ
    -2.62
    ucc
    -2.61
    ォ
    -2.61
    alore
    -2.59
    byss
    -2.57
     manner
    -2.57
    テ
    -2.51
     Gaul
    -2.47
    POSITIVE LOGITS
    12
    4.49
     12
    4.42
     13
    3.77
    13
    3.72
     11
    3.38
     119
    3.35
    11
    3.33
     1200
    3.22
     1300
    3.19
     122
    3.01
    Activations Density 0.020%

    No Known Activations