© 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. 14343
    Prev
    Next
    INDEX
    Explanations

    phrases related to undermining or weakening something or someone

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

    phrases related to the concept of undermining authority or integrity

    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
    2:0.09
    3:0.12
    4:0.01
    5:0.03
    6:0.05
    7:0.13
    8:0.12
    9:0.12
    10:0.07
    11:0.16
    Negative Logits
    INGTON
    -1.27
     mosqu
    -1.19
    lication
    -1.13
    soDeliveryDate
    -1.12
    wine
    -1.11
     ready
    -1.10
    akeru
    -1.09
    Lago
    -1.07
     watches
    -1.05
    rollers
    -1.05
    POSITIVE LOGITS
     reputation
    1.52
     credibility
    1.33
     libel
    1.26
     perception
    1.24
     ego
    1.22
     stereotype
    1.22
     prejudice
    1.20
     perceptions
    1.16
     presumption
    1.14
     characterization
    1.14
    Activations Density 0.023%

    No Known Activations