© 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. 7598
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters

    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
    0:0.20
    1:0.19
    2:0.05
    3:0.05
    4:0.04
    5:0.11
    6:0.05
    7:0.02
    8:0.04
    9:0.08
    10:0.07
    11:0.05
    Negative Logits
     Rig
    -1.77
     divided
    -1.72
     invari
    -1.66
     Berm
    -1.64
     Deaths
    -1.62
     silhouette
    -1.61
     Mits
    -1.58
     Buster
    -1.58
     ---------
    -1.56
     Creatures
    -1.56
    POSITIVE LOGITS
    ocument
    2.19
    mington
    2.15
    etary
    2.06
    ampunk
    1.99
    opoulos
    1.97
    stanbul
    1.97
     1050
    1.97
    ��
    1.96
    ocene
    1.96
    heastern
    1.91
    Activations Density 0.000%

    No Known Activations