© 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. 21412
    Prev
    Next
    INDEX
    Explanations

    negative indicators or phrases related to endings and conclusions

    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
    1:0.03
    2:0.03
    3:0.05
    4:0.04
    5:0.06
    6:0.02
    7:0.07
    8:0.02
    9:0.39
    10:0.02
    11:0.20
    Negative Logits
    rir
    -2.41
     into
    -2.13
    oug
    -1.97
    into
    -1.96
     reperto
    -1.96
     matured
    -1.92
     extinct
    -1.87
    bryce
    -1.85
    milo
    -1.83
    yond
    -1.79
    POSITIVE LOGITS
     point
    2.35
     Penalty
    2.26
    clamation
    2.09
     prediction
    2.09
    anges
    1.98
     criterion
    1.97
    etermination
    1.95
    utra
    1.94
    point
    1.94
    ointment
    1.94
    Activations Density 0.002%

    No Known Activations