© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 1630
    Prev
    Next
    INDEX
    Explanations

    specific numerical references and legal terms related to assemblies and policies

    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
    0:0.06
    1:0.02
    2:0.05
    3:0.06
    4:0.04
    5:0.06
    6:0.27
    7:0.02
    8:0.08
    9:0.20
    10:0.03
    11:0.04
    Negative Logits
    Lew
    -3.72
     scient
    -3.68
    Roger
    -3.62
    Morgan
    -3.59
    Mars
    -3.58
     fishes
    -3.56
     Lew
    -3.53
     Ross
    -3.53
     Putin
    -3.48
     geop
    -3.41
    POSITIVE LOGITS
     Assembly
    9.15
    Assembly
    8.73
     assembly
    7.65
    sembly
    7.57
    assembly
    7.18
     assemblies
    6.80
    assemb
    5.67
    semb
    5.05
     Sweeney
    4.83
     Sabha
    4.63
    Activations Density 0.005%

    No Known Activations