© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 20792
    Prev
    Next
    INDEX
    Explanations

    references to religious texts or principles

    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
    0:0.08
    1:0.08
    2:0.07
    3:0.08
    4:0.08
    5:0.09
    6:0.09
    7:0.08
    8:0.07
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
    ayne
    -2.98
    etsk
    -2.82
    ALSE
    -2.60
    nik
    -2.50
    anka
    -2.46
    ngth
    -2.43
    racial
    -2.42
    yang
    -2.34
    Dir
    -2.33
    acus
    -2.29
    POSITIVE LOGITS
     Instr
    2.61
     Jarvis
    2.50
     Messages
    2.38
     Bots
    2.37
     Content
    2.37
    IRC
    2.35
     Mods
    2.34
     GCC
    2.32
     Mech
    2.31
     Oracle
    2.31
    Activations Density 0.000%

    No Known Activations