© 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. 15535
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to creative works and their applications in various industries

    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
    1:0.03
    2:0.03
    3:0.03
    4:0.04
    5:0.04
    6:0.03
    7:0.05
    8:0.02
    9:0.15
    10:0.02
    11:0.47
    Negative Logits
     breaths
    -3.25
     pressures
    -3.21
     pains
    -3.04
     stresses
    -2.97
     sensations
    -2.90
     positions
    -2.88
     divisions
    -2.87
     fumes
    -2.87
     qualifiers
    -2.86
     days
    -2.81
    POSITIVE LOGITS
     artwork
    2.88
     sculpture
    2.77
     puzzle
    2.52
     art
    2.49
     literature
    2.25
    ework
    2.24
     architecture
    2.13
    abilia
    2.13
     decoration
    2.09
    gery
    2.07
    Activations Density 0.067%

    No Known Activations