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. 27562
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to media, law, and investigative reporting

    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
    0:0.07
    1:0.09
    2:0.05
    3:0.05
    4:0.06
    5:0.29
    6:0.04
    7:0.03
    8:0.05
    9:0.07
    10:0.09
    11:0.06
    Negative Logits
    bear
    -1.93
     Osiris
    -1.85
    Legend
    -1.73
    number
    -1.72
    renheit
    -1.71
    only
    -1.70
    -+
    -1.66
    mine
    -1.65
    fred
    -1.65
    leader
    -1.63
    POSITIVE LOGITS
    assetsadobe
    1.86
    ewitness
    1.81
     compr
    1.79
     piv
    1.74
    illy
    1.73
     extrap
    1.72
     guiActiveUn
    1.72
    inflamm
    1.72
     complied
    1.65
    )=(
    1.64
    Activations Density 0.001%

    No Known Activations