© 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. 5-ATT-KK
    11. 44121
    Prev
    Next
    INDEX
    Explanations

    references to media consumption and entertainment contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.14
    3:0.09
    4:0.12
    5:0.03
    6:0.04
    7:0.09
    8:0.08
    9:0.03
    10:0.16
    11:0.14
    Negative Logits
    覚醒
    -1.28
    atile
    -1.25
     versatile
    -1.25
    ailable
    -1.24
     spac
    -1.19
     Flavor
    -1.19
    ORY
    -1.19
     trait
    -1.19
    fits
    -1.19
     resilient
    -1.17
    POSITIVE LOGITS
    gnu
    1.43
    umbledore
    1.31
    scan
    1.26
     millenn
    1.25
     paused
    1.22
    dos
    1.21
    ovies
    1.21
    aunder
    1.21
     scrape
    1.19
    okemon
    1.19
    Activations Density 0.061%

    No Known Activations