© 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. 22108
    Prev
    Next
    INDEX
    Explanations

    email addresses and domain-related patterns

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.08
    1:0.03
    2:0.05
    3:0.13
    4:0.02
    5:0.09
    6:0.05
    7:0.13
    8:0.06
    9:0.04
    10:0.17
    11:0.10
    Negative Logits
     DRAG
    -1.07
     ®
    -1.01
    theless
    -0.93
    �
    -0.92
     moreover
    -0.91
     DRAGON
    -0.86
     CONTROL
    -0.85
        
    -0.84
     CARD
    -0.82
    ographically
    -0.81
    POSITIVE LOGITS
    Twe
    0.91
    __
    0.90
    Politics
    0.90
    ___
    0.87
    Story
    0.86
    omics
    0.86
    DonaldTrump
    0.85
    itbart
    0.85
    Kid
    0.83
    haw
    0.82
    Activations Density 0.040%

    No Known Activations