© 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. 16592
    Prev
    Next
    INDEX
    Explanations

    structures related to lists or enumerations of items, particularly in political or social contexts

    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
    0:0.05
    1:0.05
    2:0.08
    3:0.28
    4:0.03
    5:0.15
    6:0.02
    7:0.04
    8:0.02
    9:0.02
    10:0.18
    11:0.02
    Negative Logits
    ��
    -2.75
    ibe
    -2.31
    pez
    -2.20
    edin
    -2.20
    anse
    -2.16
    ilage
    -2.16
    enne
    -2.14
    auntlet
    -2.09
    acan
    -2.05
    wow
    -2.03
    POSITIVE LOGITS
     listed
    2.58
     names
    2.50
     murderers
    2.40
    listed
    2.40
     occupations
    2.34
     crimes
    2.33
     threats
    2.28
     locations
    2.28
     favorites
    2.28
     candidates
    2.28
    Activations Density 0.109%

    No Known Activations