© 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. 43565
    Prev
    Next
    INDEX
    Explanations

    quantifiers and adjectives that express intensity or degree

    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
    0:0.17
    1:0.10
    2:0.04
    3:0.11
    4:0.05
    5:0.11
    6:0.06
    7:0.03
    8:0.14
    9:0.04
    10:0.05
    11:0.05
    Negative Logits
    argument
    -1.71
    Synopsis
    -1.67
    HI
    -1.67
     append
    -1.52
     […]
    -1.52
    initial
    -1.50
    Abstract
    -1.45
    Description
    -1.44
    article
    -1.44
    Board
    -1.40
    POSITIVE LOGITS
    sers
    1.69
    thumbnails
    1.68
    eous
    1.63
    etheless
    1.58
    -$
    1.57
    eful
    1.56
    velt
    1.52
    Malley
    1.51
    rican
    1.51
    retty
    1.48
    Activations Density 0.001%

    No Known Activations