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

    Neuronpedia

    Jacobian LensNEW
    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. 22230
    Prev
    Next
    INDEX
    Explanations

    statements of fact or assertions followed by verb phrases

    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
    0:0.05
    1:0.05
    2:0.11
    3:0.05
    4:0.04
    5:0.04
    6:0.21
    7:0.03
    8:0.03
    9:0.28
    10:0.03
    11:0.03
    Negative Logits
    ��
    -3.96
     Mog
    -3.76
     ic
    -3.58
     Goth
    -3.47
     Haf
    -3.46
     scaven
    -3.39
    Yan
    -3.29
    �
    -3.27
     Ninja
    -3.27
    Graham
    -3.27
    POSITIVE LOGITS
     Pos
    6.96
    Position
    6.59
    Pos
    6.17
     POS
    6.11
     Position
    5.98
    position
    5.74
     positional
    5.58
     position
    5.54
     positions
    5.53
    POS
    5.50
    Activations Density 0.003%

    No Known Activations