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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 13774
    Prev
    Next
    INDEX
    Explanations

    positive sentiments or beliefs towards a specific entity or idea

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.12
    3:0.04
    4:0.36
    5:0.04
    6:0.02
    7:0.03
    8:0.08
    9:0.13
    10:0.04
    11:0.02
    Negative Logits
     rake
    -1.51
    \/\/
    -1.36
     copyrighted
    -1.35
     revenue
    -1.34
     promotions
    -1.33
    版
    -1.29
     buzz
    -1.29
    lem
    -1.24
    =\"
    -1.23
    ゼ
    -1.21
    POSITIVE LOGITS
    mma
    1.62
    idi
    1.60
    ework
    1.52
    iceps
    1.45
    pecting
    1.44
     Spartans
    1.41
    vim
    1.41
    Aid
    1.40
    itud
    1.39
    olate
    1.39
    Activations Density 0.001%

    No Known Activations