© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3314
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or influence over long periods of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.06
    2:0.16
    3:0.07
    4:0.05
    5:0.10
    6:0.08
    7:0.08
    8:0.05
    9:0.08
    10:0.05
    11:0.03
    Negative Logits
    Tex
    -2.62
     asylum
    -2.39
     Expansion
    -2.35
     Miracle
    -2.33
     Alien
    -2.26
     Pak
    -2.22
    ISS
    -2.21
     manif
    -2.19
    Alien
    -2.18
     advers
    -2.13
    POSITIVE LOGITS
     deprecated
    4.92
    recated
    3.72
    solete
    2.98
     Ember
    2.92
    ecycle
    2.89
     repealed
    2.88
    olicy
    2.86
    arij
    2.77
     obsolete
    2.74
     recy
    2.63
    Activations Density 0.000%

    No Known Activations