© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22183
    Prev
    Next
    INDEX
    Explanations

    numerical values and scores related to ranking or performance

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.13
    1:0.02
    2:0.11
    3:0.13
    4:0.03
    5:0.08
    6:0.04
    7:0.08
    8:0.03
    9:0.07
    10:0.16
    11:0.08
    Negative Logits
     Photographer
    -1.01
     Berger
    -0.98
    geist
    -0.97
     Investor
    -0.97
     Lent
    -0.97
     Akin
    -0.96
     Expect
    -0.95
    ouf
    -0.94
     Muse
    -0.94
     Betsy
    -0.94
    POSITIVE LOGITS
     apiece
    1.75
     totaling
    1.24
     consecut
    1.24
     respectively
    1.21
     thirds
    1.11
     increments
    1.09
    undred
    1.08
     consecutive
    1.07
    secut
    1.05
     pairs
    1.05
    Activations Density 0.492%

    No Known Activations