Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 2820
    Prev
    Next
    INDEX
    Explanations

    statements attributed to sources or individuals with insider knowledge about a situation

    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
    0:0.01
    1:0.01
    2:0.10
    3:0.09
    4:0.04
    5:0.03
    6:0.04
    7:0.04
    8:0.02
    9:0.05
    10:0.34
    11:0.16
    Negative Logits
    Interstitial
    -1.62
     repeal
    -1.38
     hemorrh
    -1.37
     invincible
    -1.34
     repealing
    -1.29
     victories
    -1.26
     cures
    -1.26
     merits
    -1.26
    ワ
    -1.25
     triumph
    -1.25
    POSITIVE LOGITS
    anu
    1.45
     Azerbai
    1.42
     interviewed
    1.39
    earcher
    1.37
     uncovered
    1.36
    tsky
    1.33
    panel
    1.30
     Scand
    1.29
    Dim
    1.27
    Lat
    1.25
    Activations Density 0.054%

    No Known Activations