© 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. 2-ATT-KK
    11. 22540
    Prev
    Next
    INDEX
    Explanations

    phrases indicating agreement or compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    information related to legal cases, government actions, and disputes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.15
    3:0.07
    4:0.22
    5:0.04
    6:0.02
    7:0.01
    8:0.18
    9:0.11
    10:0.04
    11:0.02
    Negative Logits
    ️
    -1.51
    gram
    -1.48
    aquin
    -1.29
    enth
    -1.27
    nan
    -1.27
    cci
    -1.27
    Tech
    -1.26
    zu
    -1.21
    grain
    -1.20
    chel
    -1.18
    POSITIVE LOGITS
     agre
    1.59
     reciproc
    1.58
     bargain
    1.50
     fate
    1.46
     acknow
    1.44
     contracts
    1.37
     arrang
    1.36
     voluntary
    1.35
     agreement
    1.32
     arbitration
    1.31
    Activations Density 0.012%

    No Known Activations