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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3177
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in significant events or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.03
    2:0.08
    3:0.04
    4:0.06
    5:0.05
    6:0.22
    7:0.04
    8:0.06
    9:0.19
    10:0.02
    11:0.05
    Negative Logits
     Hugo
    -4.25
     Fur
    -4.03
    fur
    -3.58
     Saber
    -3.41
     Fut
    -3.30
     poets
    -3.24
     Yus
    -3.18
     Ariel
    -3.17
     Fel
    -3.13
     Prometheus
    -3.11
    POSITIVE LOGITS
     McD
    10.94
    Mc
    6.13
     McN
    5.54
     McDonald
    4.76
    McC
    4.71
     McC
    4.70
     McM
    4.63
     McK
    4.58
     McInt
    4.53
     McH
    4.31
    Activations Density 0.001%

    No Known Activations