© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 38333
    Prev
    Next
    INDEX
    Explanations

    aspects of performance and evaluation related to productivity and resource management

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.12
    3:0.22
    4:0.14
    5:0.04
    6:0.03
    7:0.08
    8:0.08
    9:0.04
    10:0.07
    11:0.07
    Negative Logits
     prostitutes
    -1.58
     bunker
    -1.48
     pled
    -1.45
     mercenaries
    -1.38
     foreskin
    -1.30
    Downloadha
    -1.29
    bryce
    -1.28
     condoms
    -1.26
     believers
    -1.26
     Belg
    -1.26
    POSITIVE LOGITS
    irtual
    1.92
    ]),
    1.76
    IAS
    1.72
    iguous
    1.69
    eming
    1.50
     Ratio
    1.50
    ealous
    1.48
     effectively
    1.45
    ]).
    1.42
    nesota
    1.42
    Activations Density 0.120%

    No Known Activations