© 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. 17493
    Prev
    Next
    INDEX
    Explanations

    transitional phrases and conjunctions that indicate time or sequence

    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
    0:0.18
    1:0.04
    2:0.10
    3:0.07
    4:0.05
    5:0.06
    6:0.07
    7:0.06
    8:0.14
    9:0.07
    10:0.05
    11:0.04
    Negative Logits
     Ying
    -3.40
     Pyrrha
    -3.24
     Gospel
    -3.15
     Xiao
    -3.12
     Xie
    -3.05
     Mich
    -2.98
     Xue
    -2.98
     Giov
    -2.95
     Jaune
    -2.94
     migrant
    -2.93
    POSITIVE LOGITS
     Atari
    7.78
    Arcade
    3.69
    DOS
    3.64
     Commodore
    3.55
     AOL
    3.52
     Spielberg
    3.49
     2600
    3.48
     arcade
    3.46
     Alto
    3.43
     DOS
    3.16
    Activations Density 0.000%

    No Known Activations