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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 21861
    Prev
    Next
    INDEX
    Explanations

    nouns and time periods related to historical contexts and events

    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
    0:0.12
    1:0.03
    2:0.17
    3:0.10
    4:0.03
    5:0.13
    6:0.03
    7:0.03
    8:0.18
    9:0.06
    10:0.05
    11:0.02
    Negative Logits
     Obi
    -1.32
     answ
    -1.32
     physic
    -1.23
     oste
    -1.22
    POSE
    -1.21
     practition
    -1.19
    Scient
    -1.19
     aber
    -1.15
     Petty
    -1.14
     astroph
    -1.13
    POSITIVE LOGITS
    ecycle
    1.75
    ixties
    1.68
    waves
    1.66
     cycle
    1.58
     region
    1.58
     arena
    1.55
     aisle
    1.54
    region
    1.50
     confines
    1.49
     era
    1.48
    Activations Density 0.008%

    No Known Activations