© 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. 5-ATT-KK
    11. 25634
    Prev
    Next
    INDEX
    Explanations

    instances of various verbs and their variations, particularly in contextual discussions or mentions of cinematic or political themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.15
    1:0.46
    2:0.03
    3:0.02
    4:0.02
    5:0.12
    6:0.02
    7:0.02
    8:0.03
    9:0.04
    10:0.03
    11:0.02
    Negative Logits
    nex
    -2.22
    month
    -2.10
    ds
    -1.99
    ブ
    -1.91
    Num
    -1.89
    num
    -1.89
    come
    -1.88
    phrase
    -1.85
    tc
    -1.84
    rim
    -1.84
    POSITIVE LOGITS
     importing
    3.28
     storing
    3.02
     constructing
    2.92
     transferring
    2.87
     injecting
    2.85
     uploading
    2.81
     accessing
    2.77
     converting
    2.76
     pressuring
    2.73
     generating
    2.73
    Activations Density 0.121%

    No Known Activations