© 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. 5-ATT-KK
    11. 28224
    Prev
    Next
    INDEX
    Explanations

    financial figures and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.21
    1:0.31
    2:0.03
    3:0.03
    4:0.03
    5:0.14
    6:0.02
    7:0.01
    8:0.07
    9:0.04
    10:0.03
    11:0.02
    Negative Logits
     seiz
    -2.23
     Authors
    -2.02
    bush
    -1.99
     Ambro
    -1.87
     Surviv
    -1.77
     Place
    -1.76
     behav
    -1.76
     Views
    -1.73
    yout
    -1.70
     srfAttach
    -1.70
    POSITIVE LOGITS
    の魔
    2.55
     310
    2.38
    ��士
    2.37
     370
    2.35
     325
    2.29
     330
    2.28
    330
    2.25
     321
    2.24
     295
    2.16
     320
    2.14
    Activations Density 0.034%

    No Known Activations