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. 10-ATT-KK
    6. 14706
    Prev
    Next
    INDEX
    Explanations

    instances of police misconduct or violations of a plaintiff's rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.05
    2:0.13
    3:0.04
    4:0.08
    5:0.02
    6:0.17
    7:0.15
    8:0.03
    9:0.06
    10:0.08
    11:0.05
    Negative Logits
    soDeliveryDate
    -2.35
    sav
    -2.35
    inav
    -2.15
    ascus
    -2.15
     Uzbek
    -2.12
     ambassadors
    -2.11
    incinn
    -2.09
     Subaru
    -2.04
    raised
    -2.04
     Stab
    -2.02
    POSITIVE LOGITS
     Defendant
    5.20
     Plaintiff
    4.98
     Defendants
    4.97
     defendant
    3.80
     plaintiff
    3.64
     Plaint
    3.64
     defendants
    3.41
     Judge
    2.98
     plaintiffs
    2.86
    Judge
    2.81
    Activations Density 0.025%

    No Known Activations