© 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. 12333
    Prev
    Next
    INDEX
    Explanations

    references to formal statements and quotes made by individuals, particularly in political 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
    0:0.10
    1:0.02
    2:0.04
    3:0.06
    4:0.10
    5:0.04
    6:0.28
    7:0.06
    8:0.03
    9:0.16
    10:0.02
    11:0.02
    Negative Logits
    Elsa
    -2.85
     Macy
    -2.69
     rabbit
    -2.60
     bulls
    -2.59
     cows
    -2.54
     Razer
    -2.53
     Cinderella
    -2.50
     Calais
    -2.48
     Cadillac
    -2.45
    canon
    -2.40
    POSITIVE LOGITS
     Plant
    2.83
     String
    2.54
    Unit
    2.36
     Transform
    2.32
     Shape
    2.32
     Spell
    2.29
    ENTS
    2.27
     Bomb
    2.27
     Bombs
    2.25
    )].
    2.24
    Activations Density 0.218%

    No Known Activations