© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 3540
    Prev
    Next
    INDEX
    Explanations

    statements or quotes made by individuals regarding specific topics

    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
    0:0.04
    1:0.03
    2:0.04
    3:0.08
    4:0.10
    5:0.06
    6:0.08
    7:0.11
    8:0.12
    9:0.06
    10:0.04
    11:0.18
    Negative Logits
     (£
    -3.06
     Nato
    -2.99
     organise
    -2.77
     practise
    -2.74
     Horizon
    -2.71
     NEC
    -2.66
     harbour
    -2.52
     organising
    -2.52
    tein
    -2.48
     Thai
    -2.48
    POSITIVE LOGITS
    �
    6.32
    �
    4.31
    ---
    4.15
    ​​
    4.14
    ■
    4.01
    †
    3.95
    «
    3.93
    ●
    3.89
    ^{
    3.82
    �
    3.79
    Activations Density 0.087%

    No Known Activations