© 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. 7635
    Prev
    Next
    INDEX
    Explanations

    references to specific actions or processes 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
    0:0.03
    1:0.02
    2:0.04
    3:0.05
    4:0.07
    5:0.48
    6:0.01
    7:0.03
    8:0.02
    9:0.15
    10:0.02
    11:0.03
    Negative Logits
     rarely
    -3.12
     routinely
    -3.08
     preferring
    -3.05
    arcity
    -3.00
    often
    -2.96
     inconsist
    -2.92
     disproportionately
    -2.88
     seldom
    -2.83
    none
    -2.77
     frequently
    -2.76
    POSITIVE LOGITS
    Firstly
    4.75
    First
    3.81
     shall
    3.80
    Alright
    3.74
     commence
    3.66
     THEN
    3.40
    Let
    3.38
    rawdownloadcloneembedreportprint
    3.38
     here
    3.34
    Okay
    3.23
    Activations Density 0.589%

    No Known Activations