© 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. 2-ATT-KK
    11. 21674
    Prev
    Next
    INDEX
    Explanations

    instances of names and locations related to news stories

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.05
    1:0.03
    2:0.12
    3:0.07
    4:0.06
    5:0.21
    6:0.03
    7:0.05
    8:0.07
    9:0.09
    10:0.12
    11:0.05
    Negative Logits
     flavour
    -1.10
     Reserve
    -0.84
     Picks
    -0.83
     quota
    -0.82
     //[
    -0.82
     mould
    -0.82
     trophy
    -0.82
     enqu
    -0.81
     round
    -0.81
     juicy
    -0.81
    POSITIVE LOGITS
    arently
    1.03
     bicycl
    1.01
    cffff
    0.98
    posing
    0.98
    viol
    0.98
     respectively
    0.97
    lication
    0.95
    appropriately
    0.95
    efully
    0.94
    VERSION
    0.94
    Activations Density 0.048%

    No Known Activations