© 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. 12501
    Prev
    Next
    INDEX
    Explanations

    words related to concepts of freedom and morality

    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
    0:0.05
    1:0.32
    2:0.04
    3:0.08
    4:0.04
    5:0.04
    6:0.12
    7:0.04
    8:0.02
    9:0.13
    10:0.04
    11:0.03
    Negative Logits
    ancer
    -3.04
    atorium
    -2.74
    kamp
    -2.62
    heid
    -2.47
     Marathon
    -2.46
     HRC
    -2.44
    Profile
    -2.40
    vati
    -2.40
    icion
    -2.40
     Jenner
    -2.39
    POSITIVE LOGITS
    things
    5.88
     things
    5.78
     thing
    5.47
     Thing
    5.24
     Things
    5.15
    thing
    5.14
    Things
    5.07
    stuff
    5.03
     stuff
    4.46
     Stuff
    4.04
    Activations Density 0.014%

    No Known Activations