© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 22934
    Prev
    Next
    INDEX
    Explanations

    names of locations, particularly focusing on the state of New Jersey and its context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.03
    2:0.03
    3:0.19
    4:0.04
    5:0.03
    6:0.04
    7:0.37
    8:0.01
    9:0.04
    10:0.03
    11:0.07
    Negative Logits
     JD
    -2.61
     Rhod
    -2.58
     Jord
    -2.50
     Meyer
    -2.43
    Mart
    -2.40
     nep
    -2.36
     Lynd
    -2.36
     Nep
    -2.35
     JJ
    -2.34
     Mits
    -2.33
    POSITIVE LOGITS
     inciner
    2.54
    posure
    2.26
     Garfield
    2.23
     exerc
    2.18
    756
    2.17
    ulton
    2.13
    anski
    2.12
     rehe
    2.10
     shaving
    2.10
    cum
    2.10
    Activations Density 0.007%

    No Known Activations