© 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. 12715
    Prev
    Next
    INDEX
    Explanations

    Twitter handle mentions within the text

    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
    1:0.04
    2:0.11
    3:0.13
    4:0.17
    5:0.07
    6:0.08
    7:0.06
    8:0.04
    9:0.10
    10:0.04
    11:0.05
    Negative Logits
     Gmail
    -2.68
     WhatsApp
    -2.67
     withdrawals
    -2.59
     Gravity
    -2.57
     Hoff
    -2.52
     Tooth
    -2.43
     Huawei
    -2.41
     graphene
    -2.37
     Bitcoins
    -2.31
     Dropbox
    -2.29
    POSITIVE LOGITS
    sonian
    2.98
    NBA
    2.90
    dar
    2.71
    CAST
    2.54
    shi
    2.53
    issance
    2.47
    ortment
    2.47
    IAS
    2.44
    iesta
    2.40
    cott
    2.40
    Activations Density 0.020%

    No Known Activations