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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9289
    Prev
    Next
    INDEX
    Explanations

    consistently repeating conjunctions or phrases that indicate connections between ideas

    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
    0:0.10
    1:0.05
    2:0.03
    3:0.16
    4:0.07
    5:0.14
    6:0.03
    7:0.08
    8:0.05
    9:0.15
    10:0.03
    11:0.05
    Negative Logits
    DIV
    -2.00
    ��
    -1.98
     alas
    -1.97
    ardless
    -1.86
    fortunately
    -1.77
    strip
    -1.76
     convol
    -1.72
     unfocusedRange
    -1.70
    arse
    -1.70
    Split
    -1.68
    POSITIVE LOGITS
    thood
    1.99
    ococ
    1.91
     Achievements
    1.91
     Merch
    1.89
    ibli
    1.84
     Restaur
    1.80
     Mehran
    1.77
    ructose
    1.75
     advertisements
    1.74
    mone
    1.72
    Activations Density 0.005%

    No Known Activations