© 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. 17455
    Prev
    Next
    INDEX
    Explanations

    the term "ser," likely indicating a focus on a specific identifier or title in a context

    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
    1:0.08
    2:0.08
    3:0.07
    4:0.09
    5:0.07
    6:0.08
    7:0.09
    8:0.07
    9:0.08
    10:0.09
    11:0.07
    Negative Logits
     Loud
    -2.74
    azz
    -2.68
    sle
    -2.61
    NAS
    -2.60
    Lat
    -2.59
     ASUS
    -2.57
    tics
    -2.44
    sc
    -2.42
    itate
    -2.40
    Syn
    -2.40
    POSITIVE LOGITS
     Ys
    3.05
     Pension
    3.02
    imaru
    2.84
     Yuk
    2.82
    ��
    2.82
     Wynne
    2.82
     counselling
    2.71
     Ontario
    2.70
     pension
    2.56
     largeDownload
    2.53
    Activations Density 0.000%

    No Known Activations