© 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. 3-ATT-KK
    11. 5500
    Prev
    Next
    INDEX
    Explanations

    instances of the word "In" and its variations, suggesting a focus on locations or contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.17
    1:0.05
    2:0.09
    3:0.04
    4:0.07
    5:0.02
    6:0.17
    7:0.06
    8:0.03
    9:0.03
    10:0.15
    11:0.05
    Negative Logits
    folk
    -1.26
     largeDownload
    -1.23
    ctica
    -1.21
    ↵ 
    -1.13
    vine
    -1.11
    bnb
    -1.11
    ''.
    -1.09
     |--
    -1.08
    rolet
    -1.08
     �
    -1.05
    POSITIVE LOGITS
    pport
    1.33
    ject
    1.31
    antz
    1.24
    avorite
    1.20
    jection
    1.16
    uber
    1.15
    xual
    1.11
    ModLoader
    1.10
    organic
    1.07
     whiff
    1.06
    Activations Density 0.010%

    No Known Activations