© 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. 22585
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly related to statistics or financial data

    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
    0:0.15
    1:0.04
    2:0.05
    3:0.07
    4:0.02
    5:0.05
    6:0.16
    7:0.04
    8:0.08
    9:0.23
    10:0.03
    11:0.03
    Negative Logits
     Bicycle
    -3.55
     Ras
    -3.44
     Bradley
    -3.39
    uthor
    -3.26
     Beaver
    -3.19
     Hamb
    -3.09
     photoc
    -3.06
     tomato
    -3.06
     Buckingham
    -2.99
     Breast
    -2.92
    POSITIVE LOGITS
     FX
    9.09
    FX
    8.17
    fx
    6.30
    fy
    4.14
    FK
    4.06
     Fargo
    3.77
    TX
    3.69
    FW
    3.61
     Fey
    3.55
    FY
    3.54
    Activations Density 0.001%

    No Known Activations