© 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. 10-ATT-KK
    11. 14900
    Prev
    Next
    INDEX
    Explanations

    phrases indicating media coverage and public reception of films or artists

    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
    0:0.02
    1:0.02
    2:0.02
    3:0.05
    4:0.07
    5:0.03
    6:0.05
    7:0.08
    8:0.01
    9:0.17
    10:0.02
    11:0.41
    Negative Logits
     hatched
    -2.68
     inefficient
    -2.43
    Plan
    -2.42
    operated
    -2.38
     planner
    -2.29
    iland
    -2.28
    vable
    -2.24
    destruct
    -2.14
     plan
    -2.12
     buggy
    -2.12
    POSITIVE LOGITS
     acclaim
    4.58
     accol
    4.32
     notoriety
    4.29
     fame
    4.20
     prominence
    4.13
     prestige
    3.79
     endorsements
    3.73
     reputation
    3.65
     recognition
    3.63
     credibility
    3.57
    Activations Density 0.228%

    No Known Activations