© 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. 15955
    Prev
    Next
    INDEX
    Explanations

    speeches or statements related to political or societal issues, particularly those containing controversial or critical content

    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
    0:0.07
    1:0.03
    2:0.18
    3:0.03
    4:0.17
    5:0.09
    6:0.03
    7:0.03
    8:0.10
    9:0.13
    10:0.06
    11:0.02
    Negative Logits
    Gall
    -1.29
    MRI
    -1.28
    CONCLUS
    -1.27
    Analysis
    -1.21
     Flavoring
    -1.19
    Failure
    -1.18
    Activity
    -1.18
    article
    -1.17
    wcsstore
    -1.17
    CLOSE
    -1.16
    POSITIVE LOGITS
    inki
    1.44
    schild
    1.42
    aii
    1.41
    edu
    1.39
    ogun
    1.28
    nir
    1.26
    ooth
    1.25
    wei
    1.24
    zee
    1.24
    ashi
    1.23
    Activations Density 0.006%

    No Known Activations