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. 5-ATT-KK
    6. 3045
    Prev
    Next
    INDEX
    Explanations

    pronouns and references to individuals, emphasizing personal agency and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.06
    3:0.13
    4:0.19
    5:0.03
    6:0.14
    7:0.13
    8:0.07
    9:0.03
    10:0.06
    11:0.07
    Negative Logits
     Thumbnails
    -1.89
    thumbnails
    -1.53
     Fantasy
    -1.45
    版
    -1.41
    ══
    -1.40
    Offline
    -1.39
    Enh
    -1.38
    Vector
    -1.38
    ANC
    -1.35
    CLUS
    -1.31
    POSITIVE LOGITS
     bothered
    1.68
     chosen
    1.43
    erous
    1.38
     bother
    1.37
     seeming
    1.30
     bothers
    1.28
     spends
    1.28
     replied
    1.27
     volunteered
    1.27
     heck
    1.25
    Activations Density 0.006%

    No Known Activations