© 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. 13145
    Prev
    Next
    INDEX
    Explanations

    connections to physical locations, positions, or arrangements in narrative contexts

    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
    0:0.02
    1:0.02
    2:0.02
    3:0.03
    4:0.04
    5:0.24
    6:0.02
    7:0.07
    8:0.01
    9:0.41
    10:0.01
    11:0.05
    Negative Logits
     succeeds
    -2.70
     expires
    -2.35
     exceeded
    -2.34
     Secondly
    -2.32
     culmin
    -2.31
     exceed
    -2.29
     surpassed
    -2.26
     exceeds
    -2.23
     occurs
    -2.21
    ikers
    -2.18
    POSITIVE LOGITS
     gazing
    3.15
     staring
    3.13
    behind
    3.06
     patiently
    2.97
     resting
    2.80
     clinging
    2.78
     silently
    2.73
     awaiting
    2.72
    bare
    2.70
     weeping
    2.65
    Activations Density 0.366%

    No Known Activations