© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 10104
    Prev
    Next
    INDEX
    Explanations

    information related to player statistics and transactions in sports

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.06
    2:0.14
    3:0.04
    4:0.04
    5:0.02
    6:0.08
    7:0.14
    8:0.04
    9:0.05
    10:0.15
    11:0.07
    Negative Logits
     Illum
    -2.69
     Lauder
    -2.67
    schild
    -2.63
    ダ
    -2.56
     Swim
    -2.54
     Bangladesh
    -2.52
     Naw
    -2.50
     Tall
    -2.44
    Ireland
    -2.44
     Dhabi
    -2.39
    POSITIVE LOGITS
     PG
    8.02
     VG
    6.46
    PG
    5.98
    VG
    5.67
     SG
    4.51
    pg
    4.46
     Nicotine
    4.12
     pg
    4.10
    PF
    3.95
     PF
    3.90
    Activations Density 0.003%

    No Known Activations