© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22013
    Prev
    Next
    INDEX
    Explanations

    instances of the word "believe" and its variations, indicating discussions of belief and convictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.05
    2:0.05
    3:0.12
    4:0.02
    5:0.07
    6:0.06
    7:0.04
    8:0.22
    9:0.07
    10:0.12
    11:0.04
    Negative Logits
    swick
    -1.30
    ggles
    -1.24
     refill
    -1.17
     workspace
    -1.14
     brill
    -1.10
     snipp
    -1.09
    gain
    -1.08
     sugg
    -1.05
     upgr
    -1.02
    ighters
    -1.01
    POSITIVE LOGITS
    Semitism
    1.29
    hovah
    1.28
    Jews
    1.20
     prophets
    1.17
    iqueness
    1.13
    uala
    1.13
    God
    1.12
     Masquerade
    1.11
     Genocide
    1.10
     Messiah
    1.09
    Activations Density 0.109%

    No Known Activations