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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7893
    Prev
    Next
    INDEX
    Explanations

    mentions of strategies and tactical approaches in various contexts

    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
    2:0.05
    3:0.11
    4:0.02
    5:0.05
    6:0.08
    7:0.31
    8:0.06
    9:0.05
    10:0.07
    11:0.10
    Negative Logits
     ILCS
    -1.26
    jriwal
    -1.24
    apsed
    -1.20
    abytes
    -1.19
    etooth
    -1.18
    andro
    -1.16
     unmarked
    -1.10
     Pastebin
    -1.10
    chuk
    -1.10
    haps
    -1.08
    POSITIVE LOGITS
     tactics
    1.29
     Warfare
    1.26
     Tactics
    1.25
    Development
    1.21
     revolving
    1.20
     intimidation
    1.19
     strategy
    1.18
     adaptations
    1.17
     adaptation
    1.12
    Adapt
    1.07
    Activations Density 0.040%

    No Known Activations