© 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. 38392
    Prev
    Next
    INDEX
    Explanations

    feature representations of specific entities or topics

    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
    0:0.04
    1:0.03
    2:0.08
    3:0.05
    4:0.06
    5:0.04
    6:0.28
    7:0.12
    8:0.04
    9:0.04
    10:0.06
    11:0.09
    Negative Logits
     narrower
    -1.51
    ��
    -1.50
    hani
    -1.48
    ufact
    -1.42
     wider
    -1.41
     specificity
    -1.38
     Bloom
    -1.35
     breadth
    -1.30
     Augusta
    -1.29
     nearest
    -1.28
    POSITIVE LOGITS
    offer
    1.41
    ebook
    1.35
    aley
    1.34
    AF
    1.30
    amph
    1.24
    called
    1.23
    uro
    1.22
    76561
    1.21
    pkg
    1.19
    abled
    1.18
    Activations Density 0.000%

    No Known Activations