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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 132
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific individuals, particularly someone named Andrew

    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
    0:0.06
    1:0.02
    2:0.04
    3:0.03
    4:0.05
    5:0.03
    6:0.16
    7:0.04
    8:0.05
    9:0.41
    10:0.02
    11:0.03
    Negative Logits
     rug
    -3.74
     collar
    -3.55
     Spectre
    -3.45
     flu
    -3.38
    zona
    -3.33
     mir
    -3.27
    Ver
    -3.23
    quin
    -3.19
     bour
    -3.17
     Qur
    -3.17
    POSITIVE LOGITS
     Andrews
    9.13
    Andrew
    8.82
     Andrew
    8.40
     Andy
    4.99
    Andy
    4.90
     AE
    4.64
     Atkinson
    4.53
     Abe
    4.24
     Ao
    4.19
     Howe
    3.95
    Activations Density 0.010%

    No Known Activations