© 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. 5-ATT-KK
    11. 36055
    Prev
    Next
    INDEX
    Explanations

    entries related to rankings and competition placements

    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
    0:0.26
    1:0.14
    2:0.04
    3:0.04
    4:0.03
    5:0.15
    6:0.03
    7:0.02
    8:0.07
    9:0.09
    10:0.04
    11:0.04
    Negative Logits
    NetMessage
    -1.90
    bah
    -1.78
    bec
    -1.73
    emp
    -1.62
     Sunder
    -1.59
    omething
    -1.54
    IDENT
    -1.53
    taboola
    -1.53
    Spe
    -1.52
    clinton
    -1.51
    POSITIVE LOGITS
     1
    2.12
     0
    2.11
     4
    2.06
     99
    1.99
     8
    1.98
     5
    1.98
     3
    1.97
     2
    1.96
     7
    1.96
     9
    1.94
    Activations Density 0.015%

    No Known Activations