© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 18355
    Prev
    Next
    INDEX
    Explanations

    concepts related to emotional reasoning versus factual evidence

    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
    0:0.07
    1:0.02
    2:0.10
    3:0.28
    4:0.03
    5:0.08
    6:0.02
    7:0.10
    8:0.09
    9:0.03
    10:0.06
    11:0.06
    Negative Logits
     Shots
    -2.57
     Laser
    -2.57
     Sprint
    -2.35
     Hot
    -2.30
     Cream
    -2.29
     Dunk
    -2.28
     Colts
    -2.26
     Breakfast
    -2.25
     Warehouse
    -2.25
     Glow
    -2.25
    POSITIVE LOGITS
     presupp
    3.44
     volunt
    3.38
     normative
    3.29
     oneself
    3.15
     fallacy
    3.14
     conformity
    3.09
     correctness
    3.09
     impossibility
    3.08
     coercive
    3.04
     prejudices
    3.04
    Activations Density 1.355%

    No Known Activations