© 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. 9-ATT-KK
    11. 6645
    Prev
    Next
    INDEX
    Explanations

    references to the series "Orange Is the New Black."

    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
    0:0.24
    1:0.01
    2:0.02
    3:0.24
    4:0.01
    5:0.09
    6:0.01
    7:0.05
    8:0.16
    9:0.01
    10:0.10
    11:0.02
    Negative Logits
     passages
    -2.61
    verbs
    -2.37
    bats
    -2.33
     lectures
    -2.26
     maneuvers
    -2.26
     debates
    -2.25
    �
    -2.24
     disse
    -2.15
    ourses
    -2.15
     mathemat
    -2.15
    POSITIVE LOGITS
    Orange
    4.31
     Orange
    3.97
    orange
    3.27
    olla
    3.11
     orange
    3.06
     Sunrise
    2.93
     Juice
    2.76
     oranges
    2.76
     Galaxy
    2.68
     Fres
    2.62
    Activations Density 0.000%

    No Known Activations