© 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. 2-ATT-KK
    11. 15484
    Prev
    Next
    INDEX
    Explanations

    keywords related to technology, such as "innovative", "developers", "maintaining", and "designs"

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.04
    1:0.03
    2:0.10
    3:0.08
    4:0.03
    5:0.11
    6:0.03
    7:0.06
    8:0.22
    9:0.07
    10:0.11
    11:0.06
    Negative Logits
     Redux
    -1.18
    BuyableInstoreAndOnline
    -1.17
    XXX
    -1.16
    anian
    -1.12
    metry
    -1.12
    liest
    -1.12
    advertisement
    -1.10
    illery
    -1.08
    orical
    -1.06
     =>
    -1.05
    POSITIVE LOGITS
     budding
    1.29
     shine
    1.24
    rouse
    1.18
     amplify
    1.15
     stranded
    1.13
     surge
    1.12
     congreg
    1.11
     victims
    1.10
     clim
    1.09
     adjust
    1.07
    Activations Density 0.068%

    No Known Activations