Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 1-ATT-KK
    6. 6260
    Prev
    Next
    INDEX
    Explanations

    terms related to fixing electronic hardware issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.19
    1:0.04
    2:0.03
    3:0.02
    4:0.05
    5:0.04
    6:0.38
    7:0.03
    8:0.03
    9:0.03
    10:0.02
    11:0.09
    Negative Logits
     Gw
    -2.24
     Vaugh
    -1.93
     Laos
    -1.91
     Winn
    -1.82
    ム
    -1.81
     �
    -1.80
     Saras
    -1.79
     Navajo
    -1.77
     \"
    -1.76
     Pigs
    -1.74
    POSITIVE LOGITS
    jri
    2.35
    atile
    2.29
    ynes
    2.17
     ingred
    2.06
    inki
    1.95
    omet
    1.94
     activ
    1.94
    cular
    1.93
    rero
    1.91
    atility
    1.90
    Activations Density 0.001%

    No Known Activations