© 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. 8218
    Prev
    Next
    INDEX
    Explanations

    terms related to foreknowledge and conspiracy theories

    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
    0:0.05
    1:0.02
    2:0.04
    3:0.08
    4:0.04
    5:0.15
    6:0.01
    7:0.03
    8:0.05
    9:0.19
    10:0.19
    11:0.10
    Negative Logits
    jriwal
    -0.98
    ampions
    -0.98
     exhilar
    -0.95
     electr
    -0.93
     stimulates
    -0.92
    oliberal
    -0.92
     stride
    -0.92
     stimulate
    -0.90
     roar
    -0.89
     mesmer
    -0.88
    POSITIVE LOGITS
     deleted
    1.29
     purported
    1.25
     spurious
    1.19
     alleged
    1.11
     deletion
    1.03
     Reported
    1.02
     redacted
    1.01
    76561
    1.01
     unidentified
    1.01
     bogus
    1.00
    Activations Density 2.049%

    No Known Activations