© 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. 47238
    Prev
    Next
    INDEX
    Explanations

    specific nouns and terms related to style, materials, and events

    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
    2:0.08
    3:0.04
    4:0.06
    5:0.02
    6:0.43
    7:0.04
    8:0.03
    9:0.04
    10:0.09
    11:0.06
    Negative Logits
     Chr
    -1.55
     Hemp
    -1.37
     Breath
    -1.30
     Petroleum
    -1.29
     HK
    -1.28
     Bills
    -1.28
    KC
    -1.25
     Zed
    -1.25
     Ryu
    -1.23
    usercontent
    -1.22
    POSITIVE LOGITS
    ��
    1.53
    osi
    1.50
    ér
    1.43
    medium
    1.40
    igree
    1.38
    aint
    1.31
     guiActiveUnfocused
    1.30
    thood
    1.30
    icator
    1.30
    ellation
    1.29
    Activations Density 0.009%

    No Known Activations