© 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. 12630
    Prev
    Next
    INDEX
    Explanations

    elements associated with individuals and their actions or statements in a narrative context

    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
    0:0.08
    1:0.33
    2:0.05
    3:0.06
    4:0.11
    5:0.03
    6:0.03
    7:0.05
    8:0.03
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
    kefeller
    -2.46
    pler
    -2.37
    orno
    -2.27
    ocre
    -2.26
     uniquely
    -2.25
    atively
    -2.24
    pless
    -2.22
    othal
    -2.21
    etus
    -2.20
     lest
    -2.18
    POSITIVE LOGITS
     said
    7.05
    said
    6.36
    Said
    5.18
     Said
    4.48
     described
    4.01
     alleged
    3.98
    Asked
    3.95
     indicated
    3.90
     recalled
    3.85
     reiterated
    3.79
    Activations Density 0.299%

    No Known Activations