© 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. 2-ATT-KK
    11. 11538
    Prev
    Next
    INDEX
    Explanations

    sports-related statistics and details

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.13
    1:0.03
    2:0.12
    3:0.13
    4:0.04
    5:0.12
    6:0.07
    7:0.04
    8:0.06
    9:0.07
    10:0.09
    11:0.03
    Negative Logits
    etts
    -1.19
    quartered
    -1.16
    intendent
    -1.11
     Sidd
    -1.10
    ��
    -1.08
     Franch
    -1.06
    ridor
    -1.04
    itta
    -1.04
     Wim
    -1.03
    stal
    -1.03
    POSITIVE LOGITS
    �
    1.01
     avg
    0.99
    amp
    0.98
    min
    0.98
    keyes
    0.95
    ρ
    0.95
     interval
    0.94
    max
    0.93
     flaw
    0.93
    μ
    0.92
    Activations Density 0.032%

    No Known Activations