© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43368
    Prev
    Next
    INDEX
    Explanations

    instances of the word "leaving" and its variations, indicating a focus on abandonment or departure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.02
    2:0.09
    3:0.07
    4:0.20
    5:0.04
    6:0.04
    7:0.05
    8:0.06
    9:0.06
    10:0.11
    11:0.18
    Negative Logits
     Volunte
    -1.42
     Lent
    -1.36
    stretched
    -1.35
     ($)
    -1.34
    knit
    -1.34
     tiss
    -1.33
     Hann
    -1.33
     Eternity
    -1.31
    asin
    -1.31
     Shirt
    -1.30
    POSITIVE LOGITS
    geoning
    1.47
    renches
    1.39
     trapping
    1.37
    CLAIM
    1.34
    roxy
    1.33
     inhibitors
    1.32
    ュ
    1.31
    rosc
    1.28
    ertodd
    1.28
     consequential
    1.27
    Activations Density 0.002%

    No Known Activations