© 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. 2-ATT-KK
    11. 12620
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to cellular signaling pathways

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.07
    2:0.06
    3:0.06
    4:0.05
    5:0.06
    6:0.08
    7:0.13
    8:0.05
    9:0.10
    10:0.15
    11:0.08
    Negative Logits
    terday
    -1.27
    ebook
    -1.06
    ulhu
    -1.04
    partisan
    -1.01
    jri
    -0.98
    Russ
    -0.98
    intend
    -0.94
    uggage
    -0.94
    76561
    -0.94
    OPLE
    -0.92
    POSITIVE LOGITS
     ().
    1.07
     induction
    0.95
     synthesis
    0.94
     β
    0.93
     receptor
    0.93
     AX
    0.92
     peaks
    0.92
     acquired
    0.91
     Ax
    0.89
     vivo
    0.88
    Activations Density 0.098%

    No Known Activations