© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 42657
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulations and legal compliance

    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
    1:0.39
    2:0.02
    3:0.03
    4:0.02
    5:0.22
    6:0.05
    7:0.01
    8:0.03
    9:0.07
    10:0.04
    11:0.03
    Negative Logits
    accompan
    -2.34
    PRES
    -2.07
    flies
    -1.97
    ratulations
    -1.95
    WHERE
    -1.81
    footed
    -1.77
    Kate
    -1.76
    stood
    -1.75
    rament
    -1.72
    Rober
    -1.70
    POSITIVE LOGITS
    ic
    3.53
    ics
    2.72
    iche
    2.64
    IC
    2.63
    ico
    2.43
    aic
    2.40
    icism
    2.32
    igent
    2.26
    ostic
    2.21
    ici
    2.20
    Activations Density 0.007%

    No Known Activations