© 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. 7233
    Prev
    Next
    INDEX
    Explanations

    phrases related to rating or scoring items

    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
    0:0.04
    1:0.07
    2:0.17
    3:0.10
    4:0.12
    5:0.03
    6:0.05
    7:0.07
    8:0.09
    9:0.03
    10:0.05
    11:0.12
    Negative Logits
     Ft
    -2.36
     accountability
    -2.35
     athleticism
    -2.27
     Pt
    -2.26
     coffers
    -2.19
     hon
    -2.17
     PowerPoint
    -2.15
     $(
    -2.12
    reach
    -2.12
     srfAttach
    -2.10
    POSITIVE LOGITS
    1920
    3.81
    1800
    3.62
    1900
    3.61
    5000
    3.41
    1600
    3.41
    1945
    3.34
    1200
    3.32
    44
    3.29
    45
    3.29
    27
    3.25
    Activations Density 0.003%

    No Known Activations