© 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. 10-ATT-KK
    11. 6546
    Prev
    Next
    INDEX
    Explanations

    the names of notable individuals, particularly celebrities and athletes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.03
    3:0.05
    4:0.09
    5:0.34
    6:0.02
    7:0.03
    8:0.08
    9:0.15
    10:0.03
    11:0.08
    Negative Logits
    Their
    -2.42
    ":"/
    -2.40
    ?).
    -2.31
    their
    -2.27
     }}
    -2.26
    ":"
    -2.22
    aea
    -2.21
    they
    -2.19
     THEIR
    -2.19
     Their
    -2.17
    POSITIVE LOGITS
     Jr
    2.35
     and
    2.21
     plus
    2.16
     vanquished
    2.11
    ahl
    2.10
     Lester
    2.10
     Rudolph
    2.07
     collaborator
    2.06
    oğ
    2.04
     winner
    2.00
    Activations Density 0.107%

    No Known Activations