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. 44255
    Prev
    Next
    INDEX
    Explanations

    terms related to priorities and urgency in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.01
    2:0.08
    3:0.06
    4:0.07
    5:0.05
    6:0.36
    7:0.04
    8:0.04
    9:0.08
    10:0.09
    11:0.05
    Negative Logits
    orea
    -1.53
    pecially
    -1.42
     Mankind
    -1.37
    ONSORED
    -1.27
    ducers
    -1.27
     beware
    -1.27
     Answers
    -1.25
    initely
    -1.24
     foremost
    -1.21
     Choice
    -1.17
    POSITIVE LOGITS
     corrid
    1.43
    assian
    1.41
    ザ
    1.28
    angu
    1.28
    visory
    1.26
    endum
    1.24
    ibliography
    1.23
     opio
    1.20
    ursive
    1.20
    shake
    1.19
    Activations Density 0.290%

    No Known Activations