© 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. 10-ATT-KK
    6. 15146
    Prev
    Next
    INDEX
    Explanations

    numerical values and identifiers related to events or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.07
    2:0.04
    3:0.03
    4:0.04
    5:0.04
    6:0.03
    7:0.06
    8:0.49
    9:0.04
    10:0.04
    11:0.04
    Negative Logits
    MpServer
    -1.99
     dime
    -1.81
    ACTED
    -1.76
    Textures
    -1.76
     foss
    -1.71
     workaround
    -1.69
    obos
    -1.67
    ALT
    -1.66
    BuyableInstoreAndOnline
    -1.64
     wob
    -1.64
    POSITIVE LOGITS
     of
    5.54
    of
    5.28
     Of
    4.93
    Of
    4.73
     OF
    4.71
     thereof
    4.35
    OF
    4.02
    oft
    2.73
    onym
    2.44
    ensor
    2.22
    Activations Density 0.231%

    No Known Activations