© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-ATT-KK
    11. 21697
    Prev
    Next
    INDEX
    Explanations

    references to geographical features and locations related to migration and borders

    oai_token-act-pair · gpt-4o-miniTriggered 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
    1:0.03
    2:0.20
    3:0.06
    4:0.10
    5:0.06
    6:0.03
    7:0.02
    8:0.19
    9:0.12
    10:0.05
    11:0.02
    Negative Logits
     reinvest
    -1.34
    PDATE
    -1.31
     outp
    -1.30
    ufact
    -1.23
    fy
    -1.19
     illust
    -1.16
     filler
    -1.15
     accrued
    -1.13
     tuning
    -1.09
     ticking
    -1.09
    POSITIVE LOGITS
    topic
    1.46
    Border
    1.42
    tnc
    1.33
    rome
    1.30
     boundaries
    1.30
     checkpoint
    1.28
    Atlantic
    1.27
    border
    1.25
     checkpoints
    1.25
    Main
    1.25
    Activations Density 0.006%

    No Known Activations