© 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. 11532
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to security vulnerabilities and governmental practices

    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
    0:0.08
    1:0.02
    2:0.10
    3:0.12
    4:0.17
    5:0.05
    6:0.07
    7:0.03
    8:0.10
    9:0.11
    10:0.06
    11:0.02
    Negative Logits
    arent
    -1.18
     slightest
    -1.15
    iously
    -1.12
    chief
    -1.12
    stars
    -1.10
    ilver
    -1.09
    neys
    -1.08
     purportedly
    -1.08
     imminent
    -1.06
     tigers
    -1.05
    POSITIVE LOGITS
    eworks
    1.21
     Vend
    1.20
    inational
    1.18
     Assignment
    1.18
     toast
    1.18
    utical
    1.14
     boxed
    1.14
    arrass
    1.07
     bounded
    1.07
     streng
    1.06
    Activations Density 0.006%

    No Known Activations