© 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. 8619
    Prev
    Next
    INDEX
    Explanations

    parentheses in the text

    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
    0:0.06
    1:0.09
    2:0.07
    3:0.06
    4:0.06
    5:0.04
    6:0.14
    7:0.11
    8:0.04
    9:0.05
    10:0.16
    11:0.07
    Negative Logits
     EC
    -3.10
     cryptographic
    -3.08
     Evaluation
    -3.04
     eval
    -2.96
     crypt
    -2.86
     chip
    -2.86
    Cert
    -2.86
     Certificate
    -2.85
     decrypt
    -2.78
     V
    -2.74
    POSITIVE LOGITS
    ��
    3.43
     Roz
    3.25
    omore
    3.21
    genre
    2.97
    gemony
    2.90
    izophren
    2.88
    Russ
    2.87
    ��
    2.84
    oler
    2.81
    mins
    2.79
    Activations Density 0.000%

    No Known Activations