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. 10993
    Prev
    Next
    INDEX
    Explanations

    monetary values and financial compensation details

    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
    2:0.07
    3:0.11
    4:0.05
    5:0.09
    6:0.03
    7:0.06
    8:0.30
    9:0.02
    10:0.06
    11:0.08
    Negative Logits
    avored
    -3.79
    colored
    -3.65
     Hawai
    -3.60
     behaviors
    -3.54
     favoring
    -3.49
     counselors
    -3.42
     DACA
    -3.39
     Honolulu
    -3.38
     honoring
    -3.38
     Navajo
    -3.33
    POSITIVE LOGITS
     £
    8.72
    £
    7.68
     (£
    5.90
     realise
    5.75
     programme
    5.61
     UKIP
    5.55
     recognise
    5.54
    Labour
    5.46
    Scotland
    5.45
     ITV
    5.44
    Activations Density 0.100%

    No Known Activations