© 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. 2-ATT-KK
    6. 22786
    Prev
    Next
    INDEX
    Explanations

    words related to legislation, military service, and political activities within documents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to military personnel and their roles

    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
    0:0.04
    1:0.02
    2:0.17
    3:0.05
    4:0.29
    5:0.05
    6:0.03
    7:0.03
    8:0.10
    9:0.12
    10:0.03
    11:0.02
    Negative Logits
     rhy
    -1.39
    leys
    -1.35
    Squ
    -1.35
    NR
    -1.30
    phy
    -1.27
    Sus
    -1.25
    scrib
    -1.25
    Pir
    -1.24
    Li
    -1.21
    stories
    -1.20
    POSITIVE LOGITS
    udo
    1.61
    ccess
    1.45
    ettings
    1.45
     RELEASE
    1.33
     GEAR
    1.30
    enment
    1.29
     tongues
    1.28
     Quality
    1.26
     assist
    1.26
     Geoff
    1.25
    Activations Density 0.012%

    No Known Activations