© 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. 9-ATT-KK
    6. 10159
    Prev
    Next
    INDEX
    Explanations

    legal principles and constitutional references related to rights and powers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.04
    2:0.06
    3:0.25
    4:0.03
    5:0.09
    6:0.01
    7:0.10
    8:0.09
    9:0.01
    10:0.10
    11:0.06
    Negative Logits
     maths
    -2.46
     empath
    -2.45
     behaviours
    -2.28
     intersection
    -2.16
     uptake
    -2.11
     analys
    -2.08
     inver
    -2.08
     messaging
    -2.05
     modelling
    -2.00
     accelerator
    -1.98
    POSITIVE LOGITS
     Fees
    2.44
    uties
    2.35
     Sovere
    2.26
     Cust
    2.23
     Commerce
    2.21
    aci
    2.17
     Uniform
    2.17
     Taxes
    2.13
     Quantity
    2.13
     BaseType
    2.13
    Activations Density 0.016%

    No Known Activations