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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 20032
    Prev
    Next
    INDEX
    Explanations

    references to plastic and its associated chemical hazards

    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
    0:0.12
    1:0.05
    2:0.05
    3:0.03
    4:0.09
    5:0.02
    6:0.04
    7:0.34
    8:0.02
    9:0.03
    10:0.06
    11:0.10
    Negative Logits
    Thumbnail
    -2.24
    ャ
    -2.24
    rawdownloadcloneembedreportprint
    -2.21
     pony
    -2.19
    gpu
    -2.17
     ponies
    -2.12
    ml
    -2.10
    Flickr
    -2.08
    Screenshot
    -2.07
    �
    -2.07
    POSITIVE LOGITS
    EEK
    2.20
    ufact
    2.03
     HC
    2.02
    ould
    2.02
     shatter
    1.94
     injection
    1.93
    axter
    1.93
     Reese
    1.91
    ague
    1.90
    irus
    1.90
    Activations Density 0.007%

    No Known Activations