© 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. 12576
    Prev
    Next
    INDEX
    Explanations

    mentions of mobile phone models and specifications (specifically related to LG phones)

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mentions of LG products and their specifications

    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
    0:0.02
    1:0.05
    2:0.10
    3:0.12
    4:0.03
    5:0.04
    6:0.22
    7:0.14
    8:0.05
    9:0.06
    10:0.08
    11:0.05
    Negative Logits
     Nightmares
    -1.23
     ACTIONS
    -1.22
     PROGRAM
    -1.22
     Programs
    -1.19
     Clicker
    -1.18
     trail
    -1.17
     INCLUD
    -1.16
    taboola
    -1.15
     Neurolog
    -1.14
     Marathon
    -1.14
    POSITIVE LOGITS
    arov
    1.68
    イト
    1.47
     Bulg
    1.37
    unal
    1.27
    ADRA
    1.24
    amiya
    1.24
    asury
    1.22
    itol
    1.17
    reenshots
    1.16
    adish
    1.16
    Activations Density 0.003%

    No Known Activations