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. 7481
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or structures in sentences

    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
    0:0.03
    1:0.01
    2:0.11
    3:0.11
    4:0.18
    5:0.02
    6:0.16
    7:0.08
    8:0.04
    9:0.04
    10:0.07
    11:0.10
    Negative Logits
    ationally
    -1.56
    abouts
    -1.54
    cellaneous
    -1.46
    laws
    -1.45
    ktop
    -1.42
    aughs
    -1.37
    ��
    -1.36
    blogspot
    -1.36
    issance
    -1.35
    TED
    -1.34
    POSITIVE LOGITS
     Render
    1.21
     Sacrifice
    1.17
     Enemies
    1.16
     herald
    1.13
     Powerful
    1.12
     EntityItem
    1.11
    Bind
    1.10
     Zeus
    1.10
     forgiven
    1.08
     cryptoc
    1.07
    Activations Density 0.001%

    No Known Activations