© 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. 3-ATT-KK
    11. 5856
    Prev
    Next
    INDEX
    Explanations

    articles and indefinite articles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.06
    2:0.11
    3:0.08
    4:0.02
    5:0.05
    6:0.10
    7:0.07
    8:0.09
    9:0.08
    10:0.17
    11:0.07
    Negative Logits
    */(
    -1.07
    rations
    -0.98
    ioned
    -0.94
     heed
    -0.93
     headed
    -0.93
    ongyang
    -0.93
    sufficient
    -0.92
     Coverage
    -0.92
    cro
    -0.91
    Published
    -0.90
    POSITIVE LOGITS
     conqu
    1.01
     monog
    0.98
     Reflex
    0.93
     rite
    0.92
    osphere
    0.92
    ケ
    0.89
     Redemption
    0.89
     Indies
    0.88
    oi
    0.88
     rematch
    0.86
    Activations Density 0.263%

    No Known Activations