© 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. 2-ATT-KK
    11. 16170
    Prev
    Next
    INDEX
    Explanations

    expenses and costs mentioned in a financial context, along with related terms like penalties and travel expenses

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Head Attr Weights
    0:0.04
    1:0.04
    2:0.18
    3:0.06
    4:0.06
    5:0.10
    6:0.03
    7:0.05
    8:0.08
    9:0.20
    10:0.07
    11:0.03
    Negative Logits
    lez
    -1.61
    akuya
    -1.35
    ppo
    -1.30
    esm
    -1.25
    unks
    -1.21
     Poe
    -1.16
    zn
    -1.13
    isodes
    -1.13
    atform
    -1.12
     Oss
    -1.12
    POSITIVE LOGITS
     incurred
    1.83
    efficiency
    1.58
     totaled
    1.42
    payment
    1.36
     levied
    1.35
     computed
    1.32
     payable
    1.30
     accrued
    1.29
     commuting
    1.26
     obtained
    1.24
    Activations Density 0.011%

    No Known Activations