© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 5821
    Prev
    Next
    INDEX
    Explanations

    different forms of quotes and expressions

    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
    0:0.04
    1:0.01
    2:0.07
    3:0.06
    4:0.07
    5:0.05
    6:0.06
    7:0.20
    8:0.05
    9:0.04
    10:0.09
    11:0.21
    Negative Logits
     slang
    -1.64
     Translation
    -1.45
     ko
    -1.38
    phrase
    -1.34
     Ventures
    -1.34
    href
    -1.31
    ang
    -1.31
     Yen
    -1.31
    ||
    -1.29
    oof
    -1.27
    POSITIVE LOGITS
    judicial
    1.37
    ujah
    1.36
     accommodations
    1.33
    ividual
    1.30
     uncond
    1.25
    ailability
    1.25
     uncons
    1.23
    ream
    1.22
     contrace
    1.22
    orno
    1.22
    Activations Density 0.001%

    No Known Activations