© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 22195
    Prev
    Next
    INDEX
    Explanations

    nuanced emotional language and descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.02
    2:0.02
    3:0.04
    4:0.04
    5:0.16
    6:0.02
    7:0.03
    8:0.01
    9:0.44
    10:0.02
    11:0.12
    Negative Logits
    alions
    -2.78
    agents
    -2.77
    arers
    -2.76
    leases
    -2.72
    heres
    -2.72
     independents
    -2.71
     establishments
    -2.69
    aturdays
    -2.69
    classes
    -2.67
    stocks
    -2.65
    POSITIVE LOGITS
    ality
    2.64
    iness
    2.63
    icism
    2.42
     happening
    2.41
     difference
    2.33
     nuance
    2.31
     overhead
    2.29
    ness
    2.28
    iveness
    2.27
    iction
    2.27
    Activations Density 0.209%

    No Known Activations