© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 15777
    Prev
    Next
    INDEX
    Explanations

    religious concepts and their implications on morality and relationships

    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
    0:0.04
    1:0.03
    2:0.09
    3:0.11
    4:0.04
    5:0.12
    6:0.05
    7:0.28
    8:0.12
    9:0.02
    10:0.04
    11:0.02
    Negative Logits
    interstitial
    -2.93
    andestine
    -2.84
    thouse
    -2.77
    ADRA
    -2.65
     bona
    -2.59
     srfAttach
    -2.57
    kaya
    -2.56
    dq
    -2.43
     Tata
    -2.42
    izu
    -2.40
    POSITIVE LOGITS
     Him
    5.03
     His
    4.84
     Himself
    4.26
     sinners
    4.13
     He
    3.91
     sinful
    3.88
     Satan
    3.55
     humankind
    3.55
     mankind
    3.37
     Latter
    3.27
    Activations Density 0.183%

    No Known Activations