© 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. 12537
    Prev
    Next
    INDEX
    Explanations

    phrases and words indicating claims or positions regarding responsibility and roles in discussions

    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
    0:0.05
    1:0.04
    2:0.09
    3:0.12
    4:0.23
    5:0.09
    6:0.04
    7:0.10
    8:0.03
    9:0.08
    10:0.04
    11:0.04
    Negative Logits
     �
    -3.54
     ├
    -3.16
    ™:
    -3.16
     ―
    -3.13
     ·
    -2.95
     –
    -2.90
     (−
    -2.87
     ­
    -2.83
     �
    -2.76
    .:
    -2.70
    POSITIVE LOGITS
     gasp
    2.70
    "...
    2.58
    "!
    2.45
    ossible
    2.41
    emetery
    2.41
    herical
    2.36
    yip
    2.35
    inguishable
    2.31
    *.
    2.30
    riad
    2.27
    Activations Density 0.001%

    No Known Activations