© 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. 11705
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing events or issues, particularly medical and political in nature

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.03
    2:0.13
    3:0.09
    4:0.10
    5:0.07
    6:0.03
    7:0.03
    8:0.18
    9:0.14
    10:0.06
    11:0.03
    Negative Logits
     Nazis
    -1.43
     Egyptians
    -1.35
     grinning
    -1.25
     vanquished
    -1.22
     pens
    -1.21
    lasses
    -1.20
     smiling
    -1.17
     marg
    -1.16
     exagger
    -1.14
     circumcised
    -1.11
    POSITIVE LOGITS
    ��
    1.55
    urden
    1.53
    tions
    1.52
    hement
    1.48
    arenthood
    1.43
    issions
    1.40
    Attempts
    1.36
    SpaceEngineers
    1.34
    operation
    1.32
    imester
    1.32
    Activations Density 0.021%

    No Known Activations