© 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. 10-ATT-KK
    11. 22746
    Prev
    Next
    INDEX
    Explanations

    references to technology and smartphone features, particularly related to cameras

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.13
    1:0.05
    2:0.08
    3:0.06
    4:0.07
    5:0.03
    6:0.06
    7:0.17
    8:0.04
    9:0.05
    10:0.07
    11:0.12
    Negative Logits
    raft
    -2.33
    Bir
    -2.25
     Aether
    -2.12
    annis
    -2.07
     Hubbard
    -2.02
     atmosp
    -2.01
     Wagner
    -2.00
     Carpenter
    -1.97
    istries
    -1.97
     staffing
    -1.94
    POSITIVE LOGITS
     selfie
    5.07
     selfies
    4.81
    Snap
    2.78
     Snapchat
    2.77
     pic
    2.58
     hasht
    2.44
     Instagram
    2.39
     �
    2.35
     Instr
    2.32
     seiz
    2.27
    Activations Density 0.002%

    No Known Activations