© 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. 5-ATT-KK
    11. 27895
    Prev
    Next
    INDEX
    Explanations

    references to authoritative religious beliefs and critiques of religion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.03
    2:0.06
    3:0.12
    4:0.05
    5:0.07
    6:0.02
    7:0.03
    8:0.06
    9:0.15
    10:0.21
    11:0.07
    Negative Logits
     Prompt
    -1.24
     showc
    -1.21
     ransomware
    -1.19
     ALS
    -1.18
    senal
    -1.17
     Slug
    -1.15
    shapeshifter
    -1.15
     prank
    -1.15
     Cummings
    -1.14
     newsp
    -1.14
    POSITIVE LOGITS
     precept
    1.45
    leness
    1.44
     subord
    1.44
     utopian
    1.40
     earthly
    1.36
    growth
    1.35
     societies
    1.33
     democracies
    1.32
     trillions
    1.29
    ).[
    1.27
    Activations Density 0.914%

    No Known Activations