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. 2-ATT-KK
    6. 13712
    Prev
    Next
    INDEX
    Explanations

    geographical locations and legal entities

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.09
    1:0.02
    2:0.09
    3:0.15
    4:0.03
    5:0.08
    6:0.06
    7:0.05
    8:0.11
    9:0.08
    10:0.12
    11:0.05
    Negative Logits
    laughs
    -1.18
    iversal
    -1.15
    laughter
    -1.14
    rather
    -1.13
    adequ
    -1.13
    ithing
    -1.13
    ocrates
    -1.11
    $.
    -1.10
    wen
    -1.10
    ylan
    -1.10
    POSITIVE LOGITS
     Armory
    1.27
     brigade
    1.23
     Movement
    1.20
     Fund
    1.19
     Federation
    1.18
     debacle
    1.18
     Board
    1.17
     option
    1.16
     approach
    1.15
    ariat
    1.15
    Activations Density 0.422%

    No Known Activations