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. 3124
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically 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
    0:0.07
    1:0.07
    2:0.08
    3:0.07
    4:0.09
    5:0.09
    6:0.08
    7:0.08
    8:0.08
    9:0.06
    10:0.10
    11:0.07
    Negative Logits
     Watkins
    -2.91
     rigged
    -2.79
     Conn
    -2.60
     rigging
    -2.56
     mount
    -2.52
     Rig
    -2.52
     Lord
    -2.52
     Viper
    -2.50
     detonated
    -2.46
     radiator
    -2.46
    POSITIVE LOGITS
    INESS
    3.32
    ily
    2.98
    ANC
    2.96
    sych
    2.72
    Dream
    2.70
    essen
    2.60
    629
    2.56
    YR
    2.56
    429
    2.55
    ILY
    2.54
    Activations Density 0.000%

    No Known Activations