© 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. 9-ATT-KK
    11. 15797
    Prev
    Next
    INDEX
    Explanations

    references to rankings and lists of influential or notable entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.04
    2:0.09
    3:0.16
    4:0.03
    5:0.22
    6:0.04
    7:0.05
    8:0.05
    9:0.04
    10:0.08
    11:0.03
    Negative Logits
     statistics
    -3.45
     rankings
    -3.25
     statistic
    -3.20
     rating
    -3.15
     ranking
    -3.15
     forecasts
    -3.11
     benchmark
    -3.09
     predictions
    -3.07
     metric
    -3.06
     comparisons
    -3.00
    POSITIVE LOGITS
     Lawyers
    3.12
    alsa
    2.90
     lawy
    2.79
    ertodd
    2.65
     Activate
    2.60
    enfranch
    2.60
    ilaterally
    2.50
    afort
    2.50
     UNCLASSIFIED
    2.48
    obil
    2.47
    Activations Density 0.001%

    No Known Activations