© 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. 14885
    Prev
    Next
    INDEX
    Explanations

    phrases related to accusations and responses in a discussion or narrative context

    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
    0:0.07
    1:0.01
    2:0.07
    3:0.03
    4:0.06
    5:0.03
    6:0.28
    7:0.05
    8:0.08
    9:0.21
    10:0.02
    11:0.02
    Negative Logits
    yrinth
    -4.06
    emet
    -3.89
     Jelly
    -3.48
     Floyd
    -3.41
     fract
    -3.27
     Copper
    -3.25
    wire
    -3.17
     copper
    -3.16
     Diver
    -3.16
     Cop
    -3.15
    POSITIVE LOGITS
    Sa
    9.84
     Sa
    9.80
    sa
    5.83
     sa
    5.04
    Ma
    4.62
     SA
    4.33
     Ma
    4.30
     ta
    4.18
     Za
    4.07
     Alt
    4.02
    Activations Density 0.012%

    No Known Activations