© 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. 9-ATT-KK
    11. 4961
    Prev
    Next
    INDEX
    Explanations

    references to executable files and their associated concepts

    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
    0:0.06
    1:0.08
    2:0.06
    3:0.06
    4:0.03
    5:0.04
    6:0.27
    7:0.02
    8:0.04
    9:0.24
    10:0.02
    11:0.03
    Negative Logits
     Hayes
    -4.04
     Mills
    -3.93
     Cir
    -3.76
     Crus
    -3.65
    Hay
    -3.57
     Hust
    -3.52
     Gat
    -3.46
     Memphis
    -3.39
    MHz
    -3.38
     Hastings
    -3.37
    POSITIVE LOGITS
    Object
    7.78
    object
    7.78
     Object
    7.47
     Objects
    7.26
    objects
    7.21
     object
    6.96
     objects
    6.69
     Obj
    6.40
    Obj
    6.28
     obj
    5.64
    Activations Density 0.013%

    No Known Activations