© 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. 11394
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to contextual analysis and interpretation

    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
    0:0.05
    1:0.05
    2:0.12
    3:0.07
    4:0.03
    5:0.09
    6:0.04
    7:0.04
    8:0.09
    9:0.26
    10:0.08
    11:0.04
    Negative Logits
     sqor
    -1.53
    psey
    -1.42
    oshenko
    -1.38
    lehem
    -1.32
    Downloadha
    -1.31
    reb
    -1.31
    pees
    -1.29
     bills
    -1.27
    phies
    -1.26
    KO
    -1.25
    POSITIVE LOGITS
    icators
    1.54
     repeated
    1.33
     Context
    1.25
     perceptions
    1.23
     context
    1.20
     distortions
    1.20
    alys
    1.19
     perception
    1.19
     Attribution
    1.18
     contextual
    1.17
    Activations Density 0.014%

    No Known Activations