© 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. 22557
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscription and consent for receiving newsletters or emails

    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
    2:0.06
    3:0.21
    4:0.19
    5:0.05
    6:0.05
    7:0.04
    8:0.19
    9:0.05
    10:0.03
    11:0.02
    Negative Logits
    ....
    -2.80
    ..
    -2.76
     whilst
    -2.72
    ..."
    -2.51
     alot
    -2.48
    ](
    -2.46
     ensu
    -2.43
     practise
    -2.29
     organise
    -2.28
     -
    -2.26
    POSITIVE LOGITS
    ureen
    2.58
    icip
    2.52
     ∼
    2.28
    ocamp
    2.27
    hearted
    2.25
     Mehran
    2.19
    —
    2.16
    Connect
    2.14
    ffic
    2.13
    tale
    2.10
    Activations Density 0.009%

    No Known Activations