© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 8193
    Prev
    Next
    INDEX
    Explanations

    names of specific entities or brands

    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
    0:0.42
    1:0.04
    2:0.05
    3:0.04
    4:0.06
    5:0.03
    6:0.13
    7:0.05
    8:0.04
    9:0.02
    10:0.05
    11:0.03
    Negative Logits
    )=(
    -1.69
    catentry
    -1.63
    ategory
    -1.60
    soType
    -1.58
     lett
    -1.55
    ufact
    -1.55
    OTAL
    -1.50
    CLASSIFIED
    -1.43
     affili
    -1.41
    inally
    -1.40
    POSITIVE LOGITS
    burgh
    1.56
    ener
    1.53
    ooth
    1.45
    opian
    1.44
    jer
    1.44
     jog
    1.43
    oute
    1.42
    idan
    1.39
    onto
    1.39
    istani
    1.39
    Activations Density 0.058%

    No Known Activations