© 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. 2-ATT-KK
    11. 16137
    Prev
    Next
    INDEX
    Explanations

    quotes and reported speech within text

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.10
    1:0.04
    2:0.07
    3:0.13
    4:0.03
    5:0.11
    6:0.05
    7:0.07
    8:0.06
    9:0.08
    10:0.13
    11:0.07
    Negative Logits
    =(
    -1.14
    覚醒
    -1.06
     guiActiveUnfocused
    -1.03
    \":
    -0.99
    ?
    -0.96
    :,
    -0.93
    alist
    -0.92
    (_
    -0.91
    :-
    -0.88
     which
    -0.87
    POSITIVE LOGITS
    ichita
    1.00
     Mississ
    0.93
    nyder
    0.87
    assium
    0.84
    erves
    0.83
    ORGE
    0.82
    gency
    0.81
    iless
    0.81
    atchewan
    0.81
    untarily
    0.81
    Activations Density 0.074%

    No Known Activations