© 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. 5219
    Prev
    Next
    INDEX
    Explanations

    phrases with "done" or "on" as well as exclamatory or enthusiastic statements

    oai_token-act-pair · gpt-3.5-turbo
    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
    2:0.24
    3:0.03
    4:0.01
    5:0.03
    6:0.12
    7:0.25
    8:0.06
    9:0.04
    10:0.07
    11:0.03
    Negative Logits
    amiya
    -1.08
    omp
    -1.06
    involved
    -0.93
    mite
    -0.92
     hail
    -0.89
    DERR
    -0.89
     Destination
    -0.88
    ordinary
    -0.87
    typically
    -0.87
    503
    -0.87
    POSITIVE LOGITS
    washer
    1.20
    swick
    1.14
    alian
    1.08
    rise
    1.05
    eus
    1.03
    esson
    1.01
     latt
    0.99
    zees
    0.98
     obsc
    0.97
     Purg
    0.96
    Activations Density 0.300%

    No Known Activations