© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 21377
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers, specifically values and quantities

    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
    0:0.08
    1:0.01
    2:0.31
    3:0.10
    4:0.12
    5:0.10
    6:0.02
    7:0.01
    8:0.08
    9:0.09
    10:0.03
    11:0.01
    Negative Logits
    ITH
    -1.26
     Citation
    -1.21
    soType
    -1.21
     CLR
    -1.19
    uers
    -1.15
    shire
    -1.13
     RTX
    -1.10
     CCP
    -1.10
     Dele
    -1.10
     Auth
    -1.10
    POSITIVE LOGITS
    onym
    1.29
    osher
    1.27
    士
    1.25
    owl
    1.23
    �
    1.23
    mallow
    1.22
    icio
    1.15
    }}}
    1.14
    umper
    1.13
    whelming
    1.13
    Activations Density 0.036%

    No Known Activations