© 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. 11995
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Um" and contextual markers related to parentheses or explanations

    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
    0:0.08
    1:0.09
    2:0.09
    3:0.10
    4:0.08
    5:0.03
    6:0.12
    7:0.13
    8:0.04
    9:0.05
    10:0.07
    11:0.08
    Negative Logits
     booster
    -2.07
     polls
    -2.04
     partisan
    -1.95
     ward
    -1.93
     prov
    -1.90
     PP
    -1.88
     press
    -1.88
     cop
    -1.84
     panel
    -1.83
     ill
    -1.83
    POSITIVE LOGITS
    senal
    2.49
    olkien
    2.40
    RPG
    2.20
    Buyable
    2.19
    thritis
    2.18
    ahime
    2.18
    eli
    2.16
    oppable
    2.14
    Characters
    2.14
    ivot
    2.12
    Activations Density 0.003%

    No Known Activations