© 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. 4314
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions or qualifiers that suggest dependency or requirement

    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
    0:0.14
    1:0.02
    2:0.11
    3:0.06
    4:0.04
    5:0.07
    6:0.18
    7:0.07
    8:0.09
    9:0.10
    10:0.03
    11:0.05
    Negative Logits
     Nanto
    -4.86
     Mori
    -3.76
    bor
    -3.43
     Vale
    -3.40
    ynes
    -3.30
     Mist
    -3.26
    ipolar
    -3.25
     Municip
    -3.23
     Meteor
    -3.15
     Janeiro
    -3.12
    POSITIVE LOGITS
     Chick
    9.60
     chick
    6.03
     chickens
    4.99
     Chicken
    4.67
     chicks
    4.67
    Chicken
    4.64
     chicken
    4.60
     Cathy
    4.56
     Huckabee
    4.22
    Fal
    4.14
    Activations Density 0.002%

    No Known Activations