© 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. 1429
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal accounts or experiences involving complaints or problems

    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
    1:0.01
    2:0.19
    3:0.23
    4:0.08
    5:0.04
    6:0.02
    7:0.06
    8:0.04
    9:0.05
    10:0.14
    11:0.09
    Negative Logits
     evolves
    -1.60
     wherever
    -1.54
    aution
    -1.37
    ensor
    -1.35
     strives
    -1.35
    hyde
    -1.33
    ®,
    -1.30
     whatever
    -1.29
    assic
    -1.29
    aintain
    -1.29
    POSITIVE LOGITS
    �
    1.60
    wrote
    1.53
    ]:
    1.51
    heard
    1.49
     overheard
    1.48
    NUM
    1.45
    noticed
    1.44
    20439
    1.38
    isse
    1.35
    hare
    1.35
    Activations Density 0.165%

    No Known Activations