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. 18753
    Prev
    Next
    INDEX
    Explanations

    statistical references and numerical data related to percentages and changes over time

    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
    0:0.07
    1:0.02
    2:0.08
    3:0.19
    4:0.02
    5:0.09
    6:0.02
    7:0.04
    8:0.04
    9:0.02
    10:0.33
    11:0.02
    Negative Logits
     misunderstood
    -1.92
     Wanted
    -1.90
    punk
    -1.88
     anonymous
    -1.87
     sheltered
    -1.80
     deserted
    -1.76
     Wish
    -1.76
     doubts
    -1.73
     Wonderland
    -1.72
     anonymity
    -1.72
    POSITIVE LOGITS
     percentage
    2.52
     Pwr
    2.44
    %"
    2.43
     proportional
    2.37
    %.
    2.35
     proportion
    2.20
    illac
    2.12
     thirds
    2.11
     HAL
    2.08
    %,
    2.04
    Activations Density 0.058%

    No Known Activations