© 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. 14360
    Prev
    Next
    INDEX
    Explanations

    topics related to political discussions and fan culture

    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
    0:0.04
    1:0.03
    2:0.06
    3:0.06
    4:0.09
    5:0.36
    6:0.03
    7:0.04
    8:0.04
    9:0.15
    10:0.02
    11:0.03
    Negative Logits
     ALSO
    -3.85
     additionally
    -3.54
    instead
    -3.20
     Also
    -3.19
     furthermore
    -3.17
    ►
    -3.16
     thereby
    -3.10
    ?".
    -3.06
     Unsure
    -3.05
     moreover
    -3.01
    POSITIVE LOGITS
    bows
    2.58
     buzzing
    2.42
     blush
    2.40
    rawl
    2.40
     today
    2.39
    pires
    2.38
     lately
    2.21
    tale
    2.20
     herald
    2.20
     cruising
    2.18
    Activations Density 0.681%

    No Known Activations