Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 27565
    Prev
    Next
    INDEX
    Explanations

    mentions of communication tools and surveillance methods

    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
    2:0.07
    3:0.05
    4:0.04
    5:0.03
    6:0.40
    7:0.04
    8:0.02
    9:0.03
    10:0.11
    11:0.11
    Negative Logits
    trump
    -1.38
     Pradesh
    -1.35
    displayText
    -1.29
     hindsight
    -1.29
     Lauder
    -1.27
    者
    -1.26
     departures
    -1.25
    vable
    -1.22
    ngth
    -1.21
    oway
    -1.17
    POSITIVE LOGITS
    runs
    1.36
    icc
    1.30
    parts
    1.22
     cereal
    1.22
    theless
    1.21
     tablets
    1.20
    Downloadha
    1.14
    γ
    1.13
    whatever
    1.11
    issues
    1.11
    Activations Density 0.014%

    No Known Activations