© 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. 10869
    Prev
    Next
    INDEX
    Explanations

    assertions and beliefs, particularly around the concept of atheism

    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
    0:0.09
    1:0.09
    2:0.14
    3:0.04
    4:0.03
    5:0.04
    6:0.15
    7:0.05
    8:0.03
    9:0.23
    10:0.04
    11:0.02
    Negative Logits
     Morton
    -3.85
     Gomez
    -3.56
    ryn
    -3.55
    omez
    -3.42
     Nano
    -3.41
     Drake
    -3.35
     Olson
    -3.30
     Remy
    -3.23
    assic
    -3.22
    nr
    -3.21
    POSITIVE LOGITS
     Belief
    6.96
     belief
    6.94
     beliefs
    6.01
     believer
    6.00
     believing
    5.84
     believers
    5.80
     BEL
    5.25
     believe
    5.17
     Believe
    5.16
    bel
    5.14
    Activations Density 0.018%

    No Known Activations