© 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. 5-ATT-KK
    11. 39515
    Prev
    Next
    INDEX
    Explanations

    questions and interrogative phrases related to understanding processes or conditions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.11
    3:0.09
    4:0.12
    5:0.03
    6:0.05
    7:0.28
    8:0.04
    9:0.03
    10:0.07
    11:0.09
    Negative Logits
    interstitial
    -1.52
    ��
    -1.49
    uably
    -1.48
     laure
    -1.47
    vertisement
    -1.45
    ��
    -1.45
    aline
    -1.41
    ools
    -1.40
    ��
    -1.39
    ��極
    -1.37
    POSITIVE LOGITS
     exact
    1.61
     precise
    1.47
     exactly
    1.38
    correct
    1.36
     measurements
    1.30
     correct
    1.30
     desired
    1.29
     coordinates
    1.28
     Exactly
    1.24
    acters
    1.22
    Activations Density 0.003%

    No Known Activations