© 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. 10-ATT-KK
    11. 8609
    Prev
    Next
    INDEX
    Explanations

    references to auditory features and components in various contexts

    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
    0:0.09
    1:0.04
    2:0.04
    3:0.04
    4:0.06
    5:0.04
    6:0.03
    7:0.36
    8:0.03
    9:0.06
    10:0.03
    11:0.13
    Negative Logits
     accelerator
    -2.58
     FM
    -2.56
    afe
    -2.54
    erate
    -2.53
     Alpha
    -2.49
    Alpha
    -2.47
     audio
    -2.45
     Amateur
    -2.45
     Yar
    -2.42
     Chapel
    -2.40
    POSITIVE LOGITS
    )=(
    2.92
    さ
    2.82
    inav
    2.73
    ************
    2.71
    �
    2.67
     神
    2.66
    �
    2.61
     USSR
    2.60
    ć
    2.55
    ール
    2.52
    Activations Density 0.001%

    No Known Activations