© 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. 15878
    Prev
    Next
    INDEX
    Explanations

    URLs starting with "https://" and Twitter handles starting with "@"

    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
    0:0.06
    1:0.03
    2:0.20
    3:0.08
    4:0.03
    5:0.08
    6:0.06
    7:0.09
    8:0.05
    9:0.04
    10:0.13
    11:0.07
    Negative Logits
    ��
    -1.28
     Keyboard
    -1.21
     Trouble
    -1.11
    ーテ
    -1.09
    Keys
    -1.04
     Dys
    -1.03
    ADRA
    -1.02
     Puzzles
    -1.02
    ●
    -1.00
     Behavioral
    -0.98
    POSITIVE LOGITS
    sylv
    1.01
     haunted
    1.00
    cens
    0.98
    mite
    0.97
    apers
    0.96
    yp
    0.96
     cryptoc
    0.96
    verend
    0.91
    ertodd
    0.91
    gran
    0.90
    Activations Density 0.007%

    No Known Activations