© 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. 3-ATT-KK
    11. 5221
    Prev
    Next
    INDEX
    Explanations

    sports-related statistics and rankings

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.12
    3:0.09
    4:0.02
    5:0.03
    6:0.03
    7:0.06
    8:0.19
    9:0.22
    10:0.05
    11:0.09
    Negative Logits
    clave
    -1.27
     salesman
    -1.17
     forge
    -1.15
    forge
    -1.07
    ral
    -1.06
     casc
    -1.06
     Lah
    -1.05
    launch
    -1.03
    network
    -1.03
     looms
    -1.01
    POSITIVE LOGITS
    trak
    1.38
    ecause
    1.28
    ikuman
    1.18
     Enlight
    1.18
    verages
    1.16
    ateurs
    1.14
    Rank
    1.13
     brightest
    1.12
    cientious
    1.12
    orest
    1.11
    Activations Density 0.011%

    No Known Activations