© 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. 5345
    Prev
    Next
    INDEX
    Explanations

    the presence of locations or places in the text

    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
    0:0.01
    1:0.03
    2:0.05
    3:0.30
    4:0.01
    5:0.03
    6:0.11
    7:0.09
    8:0.05
    9:0.11
    10:0.05
    11:0.11
    Negative Logits
    ebus
    -1.34
     PsyNet
    -1.25
    ++)
    -1.05
    selves
    -1.05
    enic
    -1.04
     Rollins
    -1.04
    ardless
    -1.02
     sqor
    -1.02
    zzy
    -1.01
    River
    -1.01
    POSITIVE LOGITS
    utical
    1.65
    thood
    1.34
    igham
    1.31
    anwhile
    1.28
    gger
    1.25
     ILCS
    1.23
     disadvant
    1.22
    ciating
    1.21
    aign
    1.19
    chuk
    1.17
    Activations Density 0.014%

    No Known Activations