© 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. 10-ATT-KK
    11. 22708
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss or inquire about perceptions of flatness or elevation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.35
    2:0.05
    3:0.04
    4:0.05
    5:0.02
    6:0.07
    7:0.06
    8:0.02
    9:0.03
    10:0.12
    11:0.06
    Negative Logits
    Jenn
    -2.92
     Millenn
    -2.60
     constitu
    -2.59
     Cyborg
    -2.58
     Eth
    -2.56
    Blood
    -2.53
    女
    -2.48
    naissance
    -2.42
     Leadership
    -2.42
    Power
    -2.40
    POSITIVE LOGITS
     Flat
    8.36
     flat
    8.29
    flat
    7.74
     flats
    5.67
     flatt
    4.50
     flattened
    3.78
     square
    3.65
     fri
    3.56
     curved
    3.24
    fixed
    3.18
    Activations Density 0.026%

    No Known Activations