© 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. 19969
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing difficulty and challenges

    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
    0:0.02
    1:0.00
    2:0.18
    3:0.07
    4:0.13
    5:0.03
    6:0.08
    7:0.30
    8:0.02
    9:0.03
    10:0.06
    11:0.04
    Negative Logits
    minus
    -1.95
    ��
    -1.66
    blogspot
    -1.65
    gey
    -1.57
    inion
    -1.54
    orthy
    -1.51
    bda
    -1.51
    IU
    -1.48
    isky
    -1.48
    ��
    -1.48
    POSITIVE LOGITS
     gou
    1.77
     fragmentation
    1.70
     crush
    1.69
     cracking
    1.66
     tearing
    1.55
     hashing
    1.53
     Warfare
    1.53
     downloading
    1.51
     printing
    1.48
     mishand
    1.48
    Activations Density 0.006%

    No Known Activations