Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10190
    Prev
    Next
    INDEX
    Explanations

    proper nouns and patterns in names of people or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.03
    2:0.04
    3:0.35
    4:0.03
    5:0.03
    6:0.05
    7:0.17
    8:0.06
    9:0.05
    10:0.06
    11:0.06
    Negative Logits
    覚醒
    -1.58
    ¯
    -1.48
    anne
    -1.37
    clerosis
    -1.34
    Dash
    -1.28
    abet
    -1.28
    phant
    -1.27
    nih
    -1.27
    Termin
    -1.27
    intel
    -1.23
    POSITIVE LOGITS
     ILCS
    1.20
    ippi
    1.13
     harm
    1.09
     trough
    1.07
    SHIP
    1.07
     LP
    1.06
     purified
    1.06
     (.
    1.05
     Phelps
    1.03
     circuit
    1.02
    Activations Density 0.005%

    No Known Activations