© 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. 5-ATT-KK
    6. 42696
    Prev
    Next
    INDEX
    Explanations

    references to legal professionals or legal terminology

    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
    0:0.04
    1:0.02
    2:0.35
    3:0.09
    4:0.08
    5:0.05
    6:0.12
    7:0.03
    8:0.05
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
     Dynam
    -1.59
     gust
    -1.57
     seriousness
    -1.52
     curtains
    -1.51
     sol
    -1.50
     cynicism
    -1.47
     seiz
    -1.45
     Tol
    -1.44
     leakage
    -1.44
     semantics
    -1.43
    POSITIVE LOGITS
    ngth
    1.90
    etheless
    1.85
    thouse
    1.84
    insula
    1.81
    inces
    1.78
    utherford
    1.77
    operated
    1.72
    staking
    1.72
     differed
    1.71
    tyard
    1.66
    Activations Density 0.110%

    No Known Activations