© 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. 27702
    Prev
    Next
    INDEX
    Explanations

    instances of the word "off" in various contexts

    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
    0:0.13
    1:0.01
    2:0.17
    3:0.03
    4:0.09
    5:0.05
    6:0.08
    7:0.10
    8:0.15
    9:0.02
    10:0.06
    11:0.05
    Negative Logits
     Divinity
    -1.60
     Sixth
    -1.57
     Methodist
    -1.45
    DM
    -1.41
     Norn
    -1.40
    Bonus
    -1.40
    LV
    -1.37
    hiro
    -1.36
     Baptist
    -1.33
     dearly
    -1.31
    POSITIVE LOGITS
     depending
    1.69
    imet
    1.67
    vironment
    1.65
    depending
    1.64
     psychiat
    1.62
    othal
    1.62
    usterity
    1.61
    gradation
    1.54
    wards
    1.52
    ipolar
    1.50
    Activations Density 0.001%

    No Known Activations