© 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. 14355
    Prev
    Next
    INDEX
    Explanations

    phrases related to textual evidence and descriptions

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    instances of the word "the"

    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
    0:0.05
    1:0.04
    2:0.18
    3:0.16
    4:0.03
    5:0.03
    6:0.05
    7:0.06
    8:0.14
    9:0.04
    10:0.12
    11:0.04
    Negative Logits
    ensive
    -1.04
    ipeg
    -1.02
    olicy
    -0.98
     havoc
    -0.96
    EXT
    -0.92
    ense
    -0.92
    ibus
    -0.86
    ricular
    -0.86
    Keefe
    -0.86
    regon
    -0.84
    POSITIVE LOGITS
     alike
    1.05
    etheless
    0.97
     abbre
    0.92
     respectively
    0.92
     ↑
    0.90
    SPONSORED
    0.87
     ISI
    0.87
     Tags
    0.84
     ensuing
    0.84
     encl
    0.84
    Activations Density 0.124%

    No Known Activations