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. 7514
    Prev
    Next
    INDEX
    Explanations

    references to various social or cultural phenomena and their implications

    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
    0:0.07
    1:0.02
    2:0.13
    3:0.06
    4:0.09
    5:0.08
    6:0.02
    7:0.03
    8:0.19
    9:0.06
    10:0.07
    11:0.13
    Negative Logits
    tein
    -1.66
    heet
    -1.55
    onom
    -1.47
    apter
    -1.47
    ler
    -1.45
    heed
    -1.40
    emort
    -1.37
    tera
    -1.37
    athy
    -1.36
    farious
    -1.35
    POSITIVE LOGITS
    soDeliveryDate
    1.78
    depending
    1.66
    runners
    1.52
     enthusi
    1.42
    inline
    1.40
    Interstitial
    1.39
    ONES
    1.34
     depending
    1.33
     Schwarzenegger
    1.32
     respectively
    1.32
    Activations Density 0.018%

    No Known Activations