© 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. 2492
    Prev
    Next
    INDEX
    Explanations

    events and social media interactions related to cryptocurrency

    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
    1:0.08
    2:0.05
    3:0.03
    4:0.04
    5:0.03
    6:0.14
    7:0.03
    8:0.04
    9:0.40
    10:0.02
    11:0.03
    Negative Logits
     Rowe
    -3.54
    chester
    -3.29
     Wiley
    -3.25
    resh
    -3.21
     Jah
    -3.16
    robe
    -3.16
     Latvia
    -3.16
     Runner
    -3.12
    gem
    -3.11
     cuff
    -3.11
    POSITIVE LOGITS
     AN
    6.46
    AN
    5.13
     Ana
    5.07
     Anon
    4.87
    ANI
    4.55
     Ao
    4.50
    anth
    4.35
     Anton
    4.25
     ans
    4.23
     Hasan
    4.22
    Activations Density 0.025%

    No Known Activations