© 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. 11665
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of potential actions and outcomes

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.03
    2:0.12
    3:0.05
    4:0.05
    5:0.09
    6:0.04
    7:0.06
    8:0.16
    9:0.04
    10:0.12
    11:0.06
    Negative Logits
     Gleaming
    -0.95
    quart
    -0.93
    tery
    -0.89
    illing
    -0.82
     Mell
    -0.82
     Cly
    -0.82
     counts
    -0.80
    BuyableInstoreAndOnline
    -0.79
     deb
    -0.78
    Rare
    -0.76
    POSITIVE LOGITS
    ivably
    1.20
    inarily
    1.09
    pload
    1.09
    bably
    1.08
     someday
    1.06
    IQ
    1.00
     feas
    0.98
    imize
    0.98
    enance
    0.97
    react
    0.94
    Activations Density 0.153%

    No Known Activations