© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 11062
    Prev
    Next
    INDEX
    Explanations

    questions and responses related to ongoing legal matters

    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
    0:0.06
    1:0.07
    2:0.06
    3:0.03
    4:0.28
    5:0.14
    6:0.04
    7:0.05
    8:0.07
    9:0.06
    10:0.05
    11:0.05
    Negative Logits
     Remastered
    -2.19
    izont
    -2.15
     Inher
    -1.93
     inherit
    -1.93
    Adds
    -1.68
     simulac
    -1.66
     inher
    -1.64
     shorthand
    -1.62
     tidy
    -1.61
     Reflex
    -1.55
    POSITIVE LOGITS
    intendent
    2.14
    ONSORED
    1.99
    aban
    1.92
    heed
    1.91
    abo
    1.88
    eno
    1.88
    intend
    1.88
    aturdays
    1.79
     Sabha
    1.76
    911
    1.73
    Activations Density 0.007%

    No Known Activations