© 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. 21484
    Prev
    Next
    INDEX
    Explanations

    descriptors and phrases related to physical posture and alignment

    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
    0:0.10
    1:0.04
    2:0.04
    3:0.05
    4:0.08
    5:0.03
    6:0.03
    7:0.28
    8:0.02
    9:0.04
    10:0.04
    11:0.20
    Negative Logits
    �
    -2.49
    vironment
    -2.46
     Flan
    -2.33
     Grimm
    -2.24
     Flint
    -2.20
     Deer
    -2.16
    renheit
    -2.15
     graduate
    -2.14
     Falk
    -2.14
     Pipeline
    -2.13
    POSITIVE LOGITS
     Ces
    2.67
     largeDownload
    2.47
     Sets
    2.34
    004
    2.33
     Cot
    2.33
     Santos
    2.32
     seiz
    2.27
    inges
    2.26
     Accessories
    2.21
     cos
    2.21
    Activations Density 0.017%

    No Known Activations