© 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. 2-ATT-KK
    11. 12835
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning elements of contrast, with a focus on laws or regulations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.02
    2:0.08
    3:0.06
    4:0.05
    5:0.12
    6:0.08
    7:0.09
    8:0.05
    9:0.05
    10:0.18
    11:0.09
    Negative Logits
    ince
    -0.95
    estate
    -0.86
    otype
    -0.82
    aska
    -0.80
    izable
    -0.78
    ARP
    -0.78
    agonist
    -0.77
    steam
    -0.76
    cko
    -0.76
    ffect
    -0.76
    POSITIVE LOGITS
     alike
    1.11
     respectively
    1.02
     accordingly
    0.95
     thereafter
    0.94
     versa
    0.82
     annotations
    0.82
     therein
    0.81
     thence
    0.80
     consequently
    0.79
     consequ
    0.76
    Activations Density 0.547%

    No Known Activations