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. 5-ATT-KK
    6. 7194
    Prev
    Next
    INDEX
    Explanations

    words associated with bureaucracy and administrative processes

    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
    0:0.06
    1:0.02
    2:0.18
    3:0.07
    4:0.06
    5:0.03
    6:0.22
    7:0.03
    8:0.07
    9:0.06
    10:0.06
    11:0.09
    Negative Logits
     liner
    -1.52
     shelling
    -1.44
     rounding
    -1.41
     spikes
    -1.37
     chilling
    -1.33
     clipping
    -1.32
     clutter
    -1.31
     icing
    -1.31
     gunfire
    -1.31
     laughing
    -1.29
    POSITIVE LOGITS
    ér
    1.67
    ét
    1.64
     Mé
    1.58
    ��
    1.52
    î
    1.51
    É
    1.49
    ß
    1.46
     Femin
    1.45
     裏�
    1.44
    Joined
    1.43
    Activations Density 0.011%

    No Known Activations