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. 7-ATT-KK
    6. 18989
    Prev
    Next
    INDEX
    Explanations

    events or discussions surrounding significant tragedies and inquiries related to accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    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
    1:0.20
    2:0.02
    3:0.06
    4:0.01
    5:0.15
    6:0.31
    7:0.03
    8:0.05
    9:0.05
    10:0.01
    11:0.02
    Negative Logits
    itech
    -2.08
    Feed
    -2.01
    rentices
    -1.99
    fee
    -1.94
    aldi
    -1.92
    onga
    -1.91
    iasis
    -1.89
    Micro
    -1.88
    ono
    -1.86
    iliate
    -1.85
    POSITIVE LOGITS
     eyewitness
    2.26
     civilian
    2.16
     declass
    2.07
     Hussein
    2.01
     civilians
    2.00
     Nato
    1.97
     Saddam
    1.96
     McCain
    1.89
     remem
    1.87
     Lyndon
    1.86
    Activations Density 1.553%

    No Known Activations