© 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. 746
    Prev
    Next
    INDEX
    Explanations

    references to the concept of establishment and its influence on various situations

    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
    0:0.10
    1:0.04
    2:0.14
    3:0.05
    4:0.04
    5:0.03
    6:0.31
    7:0.05
    8:0.03
    9:0.12
    10:0.03
    11:0.02
    Negative Logits
     submar
    -3.87
     Wem
    -3.81
     Seym
    -3.72
     motel
    -3.63
     Jem
    -3.63
    コ
    -3.46
     Desmond
    -3.39
    Hart
    -3.39
     Hart
    -3.34
    Murray
    -3.30
    POSITIVE LOGITS
     Grow
    7.37
     grow
    7.07
     Growth
    7.00
    grow
    6.95
    rowth
    6.65
     growth
    6.55
    growth
    6.44
     grows
    6.22
     Growing
    5.79
     grown
    5.44
    Activations Density 0.025%

    No Known Activations