© 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. 10-ATT-KK
    11. 12939
    Prev
    Next
    INDEX
    Explanations

    patterns related to balance and its disruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.11
    1:0.20
    2:0.06
    3:0.04
    4:0.07
    5:0.02
    6:0.13
    7:0.13
    8:0.03
    9:0.04
    10:0.05
    11:0.07
    Negative Logits
     Scientology
    -2.78
    aden
    -2.75
    mouth
    -2.47
     Scient
    -2.42
    acular
    -2.39
     ghetto
    -2.27
     hood
    -2.26
    -+
    -2.23
     Compton
    -2.16
     Maur
    -2.15
    POSITIVE LOGITS
     balance
    5.91
    Balance
    5.48
     balancing
    5.23
     Balance
    5.19
     balanced
    5.12
     balances
    5.00
    balance
    4.63
    balanced
    4.55
     Balanced
    4.54
     imbalance
    3.75
    Activations Density 0.011%

    No Known Activations