© 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. 5-ATT-KK
    11. 3767
    Prev
    Next
    INDEX
    Explanations

    references to travel bans and immigration policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.01
    2:0.05
    3:0.06
    4:0.05
    5:0.04
    6:0.02
    7:0.07
    8:0.04
    9:0.06
    10:0.40
    11:0.12
    Negative Logits
     Leigh
    -1.82
     Chess
    -1.58
     Classics
    -1.53
     NAD
    -1.50
     Ashes
    -1.44
     Bian
    -1.41
    icro
    -1.40
     mole
    -1.40
     Balt
    -1.40
    ries
    -1.40
    POSITIVE LOGITS
     aimed
    2.07
     targeting
    2.04
     triggered
    1.93
     targeted
    1.86
     executed
    1.85
     predecessor
    1.80
     repeal
    1.79
     rollout
    1.76
     purported
    1.76
     effected
    1.74
    Activations Density 0.019%

    No Known Activations