© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 13541
    Prev
    Next
    INDEX
    Explanations

    references to specific dates, times, and formats related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    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
    2:0.04
    3:0.20
    4:0.04
    5:0.08
    6:0.06
    7:0.04
    8:0.03
    9:0.02
    10:0.34
    11:0.03
    Negative Logits
    %]
    -1.96
     Alone
    -1.94
     laure
    -1.88
    hare
    -1.73
     predomin
    -1.73
     2006
    -1.70
     behalf
    -1.69
     Forgotten
    -1.66
     bald
    -1.64
     Last
    -1.64
    POSITIVE LOGITS
    )!
    2.67
    )].
    2.60
    VPN
    2.52
    GMT
    2.44
    ascript
    2.40
    )),
    2.32
    )...
    2.27
    )/
    2.24
    )).
    2.19
    ),
    2.19
    Activations Density 0.021%

    No Known Activations