© 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. 14498
    Prev
    Next
    INDEX
    Explanations

    expressions of advice or strong recommendations

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

    imperatives and suggestions regarding actions

    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
    0:0.02
    1:0.03
    2:0.06
    3:0.10
    4:0.01
    5:0.04
    6:0.15
    7:0.09
    8:0.13
    9:0.11
    10:0.08
    11:0.12
    Negative Logits
     veins
    -1.43
    soever
    -1.20
     latex
    -1.18
     backlog
    -1.13
    ural
    -1.04
     allergic
    -1.04
     metic
    -1.04
     ammonia
    -1.03
     adhesive
    -1.01
     inflammatory
    -1.01
    POSITIVE LOGITS
     someday
    1.77
     ourselves
    1.56
    von
    1.18
    reci
    1.16
     emulate
    1.13
    ularity
    1.13
    joice
    1.13
    reciation
    1.12
    iners
    1.06
     celebrate
    1.03
    Activations Density 0.013%

    No Known Activations