© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 9583
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals

    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
    2:0.03
    3:0.08
    4:0.03
    5:0.05
    6:0.10
    7:0.03
    8:0.05
    9:0.44
    10:0.03
    11:0.01
    Negative Logits
     Horde
    -3.76
    ベ
    -3.42
     Harold
    -3.42
     Ambro
    -3.33
     Foo
    -3.30
     Bean
    -3.25
     Gadget
    -3.13
    RON
    -3.12
     Otto
    -3.09
     Puppet
    -3.09
    POSITIVE LOGITS
    dale
    4.71
    yss
    4.35
    seys
    4.26
    leigh
    4.05
    SK
    3.96
    sky
    3.80
    ce
    3.79
    TY
    3.76
    sey
    3.76
    na
    3.70
    Activations Density 0.006%

    No Known Activations