© 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. 47203
    Prev
    Next
    INDEX
    Explanations

    terms related to sports team selections and rankings

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.05
    2:0.18
    3:0.09
    4:0.10
    5:0.03
    6:0.06
    7:0.07
    8:0.08
    9:0.05
    10:0.11
    11:0.08
    Negative Logits
    ortium
    -1.53
    Beg
    -1.42
     Manz
    -1.39
     ⓘ
    -1.38
     Ars
    -1.32
     Imran
    -1.31
     finished
    -1.30
     ($
    -1.30
    idates
    -1.28
     coveted
    -1.27
    POSITIVE LOGITS
    inventoryQuantity
    1.45
     sensit
    1.43
     kan
    1.42
    saf
    1.39
    externalActionCode
    1.36
    notations
    1.35
     treason
    1.34
     biases
    1.32
     freedoms
    1.32
    シャ
    1.32
    Activations Density 0.001%

    No Known Activations