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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 21131
    Prev
    Next
    INDEX
    Explanations

    instances of possible misconduct or undesirable actions related to authority and compliance

    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
    0:0.04
    1:0.03
    2:0.06
    3:0.32
    4:0.03
    5:0.05
    6:0.02
    7:0.05
    8:0.03
    9:0.02
    10:0.28
    11:0.02
    Negative Logits
    dfx
    -2.08
    utenberg
    -2.04
    Weak
    -1.98
    redibly
    -1.96
    ilus
    -1.95
    knit
    -1.89
    Incre
    -1.88
    tml
    -1.86
    idth
    -1.83
    Crash
    -1.83
    POSITIVE LOGITS
     restrictions
    2.71
     mandates
    2.53
     whatsoever
    2.49
     requirement
    2.48
     guarantees
    2.48
     nor
    2.38
     forbids
    2.35
     dues
    2.34
     prohibitions
    2.34
     restriction
    2.33
    Activations Density 0.124%

    No Known Activations