© 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. 12174
    Prev
    Next
    INDEX
    Explanations

    phrases related to power or authority

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

    phrases emphasizing the concept of "power" in various contexts

    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
    0:0.01
    1:0.03
    2:0.04
    3:0.34
    4:0.02
    5:0.02
    6:0.05
    7:0.20
    8:0.04
    9:0.04
    10:0.07
    11:0.08
    Negative Logits
    anmar
    -1.42
    fif
    -1.34
    venth
    -1.33
    idel
    -1.29
    oval
    -1.21
    bush
    -1.20
    infeld
    -1.20
    estate
    -1.19
    hospital
    -1.19
    pless
    -1.19
    POSITIVE LOGITS
     imagination
    1.33
     psi
    1.28
     persuasion
    1.23
    tein
    1.22
     amplification
    1.21
     deduction
    1.20
     influence
    1.18
    thood
    1.17
     pedals
    1.16
     improvis
    1.11
    Activations Density 0.029%

    No Known Activations