© 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. 14330
    Prev
    Next
    INDEX
    Explanations

    phrases indicating strong agreement or understanding

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

    expressions of strong beliefs or emotional responses

    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
    0:0.03
    1:0.06
    2:0.13
    3:0.05
    4:0.01
    5:0.04
    6:0.13
    7:0.08
    8:0.08
    9:0.09
    10:0.11
    11:0.15
    Negative Logits
     meantime
    -1.05
     gulf
    -1.00
    ocrats
    -0.99
     Nept
    -0.96
     intervening
    -0.95
     COURT
    -0.92
    ocratic
    -0.89
     IMAGES
    -0.89
     Advertisement
    -0.88
     Paramount
    -0.87
    POSITIVE LOGITS
    poke
    1.34
    Finish
    1.24
     myself
    1.16
    redd
    1.10
    angan
    1.08
    ricular
    1.03
    edIn
    1.03
    aido
    1.01
    76561
    1.00
    yss
    1.00
    Activations Density 0.045%

    No Known Activations