© 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. 33301
    Prev
    Next
    INDEX
    Explanations

    instances of strong opinions or statements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.06
    1:0.18
    2:0.04
    3:0.07
    4:0.03
    5:0.19
    6:0.11
    7:0.01
    8:0.03
    9:0.10
    10:0.09
    11:0.03
    Negative Logits
     manufacturer
    -1.45
     endorsement
    -1.43
     NAS
    -1.34
     Antarctica
    -1.32
     Manufact
    -1.32
     Marketable
    -1.31
    manufact
    -1.31
    ワン
    -1.27
     meteor
    -1.26
    版
    -1.26
    POSITIVE LOGITS
    �
    1.81
    �
    1.80
    uggish
    1.59
    raq
    1.58
    gging
    1.57
    aq
    1.52
    tering
    1.50
    ��
    1.49
    roth
    1.49
    qqa
    1.48
    Activations Density 0.045%

    No Known Activations