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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14495
    Prev
    Next
    INDEX
    Explanations

    references to publishing and production details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.17
    1:0.15
    2:0.08
    3:0.05
    4:0.03
    5:0.02
    6:0.10
    7:0.07
    8:0.04
    9:0.06
    10:0.13
    11:0.05
    Negative Logits
    Ark
    -3.25
     Arkansas
    -2.98
     Hutchinson
    -2.80
     hawk
    -2.74
     Hank
    -2.67
     Benson
    -2.65
     bir
    -2.65
     scorp
    -2.63
    Dust
    -2.61
     Icar
    -2.60
    POSITIVE LOGITS
     Franco
    8.74
    Fran
    5.73
     Macron
    4.29
    Catal
    4.28
     Franç
    4.15
     Spani
    4.13
     Catalonia
    4.03
     Catal
    4.02
     François
    4.00
     Madrid
    3.99
    Activations Density 0.001%

    No Known Activations