© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 10248
    Prev
    Next
    INDEX
    Explanations

    adjectives and their impact in a context, particularly those describing size, quality, and emotional tones

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.24
    1:0.03
    2:0.09
    3:0.05
    4:0.11
    5:0.03
    6:0.12
    7:0.03
    8:0.10
    9:0.05
    10:0.05
    11:0.04
    Negative Logits
     Shares
    -1.59
     peers
    -1.49
     boards
    -1.47
     stret
    -1.43
    ���
    -1.43
     charts
    -1.42
     favour
    -1.42
    boards
    -1.37
     limb
    -1.37
     mitigate
    -1.36
    POSITIVE LOGITS
    araoh
    2.02
    FUL
    1.96
    leased
    1.82
    cia
    1.80
    actly
    1.78
    TextColor
    1.72
    oaded
    1.72
    \\\\
    1.69
    thodox
    1.68
    idable
    1.64
    Activations Density 0.000%

    No Known Activations