© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 13652
    Prev
    Next
    INDEX
    Explanations

    phrases related to political talking points

    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
    0:0.05
    1:0.02
    2:0.23
    3:0.07
    4:0.17
    5:0.07
    6:0.02
    7:0.02
    8:0.10
    9:0.13
    10:0.04
    11:0.02
    Negative Logits
    angular
    -1.28
    vic
    -1.26
     conclud
    -1.18
    ola
    -1.13
    iem
    -1.11
    EMP
    -1.09
    OUS
    -1.09
    issa
    -1.08
     proport
    -1.07
    teness
    -1.05
    POSITIVE LOGITS
     louder
    1.46
     Remastered
    1.36
    姫
    1.32
    uously
    1.28
    Spe
    1.27
     Collider
    1.25
     Voices
    1.25
    english
    1.22
    Song
    1.20
    culosis
    1.18
    Activations Density 0.010%

    No Known Activations