© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 9557
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulations and guidelines regarding software use and unauthorized activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.05
    2:0.19
    3:0.04
    4:0.06
    5:0.10
    6:0.06
    7:0.09
    8:0.07
    9:0.11
    10:0.06
    11:0.06
    Negative Logits
    ixties
    -1.25
     capped
    -1.18
     flesh
    -1.06
    ppers
    -1.00
     Roose
    -1.00
    CNN
    -0.99
     Kelley
    -0.98
    INAL
    -0.97
     Parish
    -0.97
     Reuters
    -0.97
    POSITIVE LOGITS
    ファ
    1.13
     Instruction
    1.12
    �
    1.08
    cise
    1.07
    …………
    1.07
    uria
    1.04
     analys
    1.04
     instr
    1.01
    グ
    1.00
    angible
    0.99
    Activations Density 0.021%

    No Known Activations