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. 13777
    Prev
    Next
    INDEX
    Explanations

    person names and locations

    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
    0:0.05
    1:0.04
    2:0.19
    3:0.06
    4:0.20
    5:0.08
    6:0.04
    7:0.03
    8:0.05
    9:0.14
    10:0.05
    11:0.03
    Negative Logits
    DragonMagazine
    -1.33
    pecially
    -1.30
    Saharan
    -1.29
    ケ
    -1.29
    uggest
    -1.28
    along
    -1.25
    BIT
    -1.24
     contrace
    -1.24
    groups
    -1.23
    ���
    -1.22
    POSITIVE LOGITS
     Spa
    1.30
     Wer
    1.24
    leen
    1.18
    riage
    1.17
     Warranty
    1.14
     improvement
    1.14
     Ended
    1.12
     Ends
    1.11
     Plate
    1.09
    ufact
    1.09
    Activations Density 0.004%

    No Known Activations