© 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. 10-ATT-KK
    11. 20359
    Prev
    Next
    INDEX
    Explanations

    numerical data related to rankings and scores

    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
    0:0.06
    1:0.08
    2:0.09
    3:0.06
    4:0.04
    5:0.02
    6:0.10
    7:0.24
    8:0.02
    9:0.03
    10:0.07
    11:0.14
    Negative Logits
    Case
    -2.09
     Kush
    -1.98
     Orth
    -1.93
     Oath
    -1.91
     Patient
    -1.91
     Caption
    -1.90
    Flow
    -1.85
     livestream
    -1.85
     Lex
    -1.84
     Letter
    -1.83
    POSITIVE LOGITS
     standings
    2.26
    ieu
    2.13
     conduc
    2.10
     points
    2.04
     bonus
    2.02
    blogspot
    1.97
     rebounds
    1.91
    FK
    1.90
    iership
    1.87
     Achievements
    1.85
    Activations Density 0.022%

    No Known Activations