© 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. 17199
    Prev
    Next
    INDEX
    Explanations

    financial metrics or references related to taxation and government reporting

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.04
    1:0.41
    2:0.06
    3:0.04
    4:0.05
    5:0.02
    6:0.05
    7:0.09
    8:0.03
    9:0.03
    10:0.07
    11:0.05
    Negative Logits
    agall
    -2.24
     plaster
    -2.21
     antagonists
    -2.21
    querade
    -2.21
    ude
    -2.19
    imum
    -2.19
    loe
    -2.16
     devil
    -2.13
     Hey
    -2.13
    hero
    -2.13
    POSITIVE LOGITS
    covered
    3.98
     covered
    3.76
     silenced
    3.70
     wrapped
    3.69
     pinned
    3.65
     folded
    3.59
    iled
    3.58
     chained
    3.56
    insured
    3.55
    leted
    3.54
    Activations Density 0.342%

    No Known Activations