© 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. 26927
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to obstruction and legal issues

    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
    0:0.02
    1:0.02
    2:0.05
    3:0.05
    4:0.10
    5:0.05
    6:0.07
    7:0.34
    8:0.04
    9:0.04
    10:0.10
    11:0.08
    Negative Logits
    variable
    -1.46
    antine
    -1.39
    alde
    -1.38
     ORIG
    -1.38
    unique
    -1.36
    版
    -1.35
    value
    -1.32
     bitters
    -1.32
    values
    -1.32
    come
    -1.32
    POSITIVE LOGITS
     pursuit
    1.59
    kB
    1.47
     obstruct
    1.36
     Ples
    1.35
     obstruction
    1.34
    rows
    1.31
     direction
    1.29
     impede
    1.28
     Telesc
    1.28
     delivery
    1.26
    Activations Density 0.004%

    No Known Activations