© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 22545
    Prev
    Next
    INDEX
    Explanations

    references to fictional storytelling and character development in music

    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
    0:0.10
    1:0.07
    2:0.04
    3:0.15
    4:0.03
    5:0.01
    6:0.25
    7:0.11
    8:0.02
    9:0.03
    10:0.05
    11:0.08
    Negative Logits
     Partner
    -2.51
     Vaj
    -2.48
     VP
    -2.40
     Panda
    -2.31
    metics
    -2.29
     Tend
    -2.23
     majors
    -2.21
     cushion
    -2.19
     Scheme
    -2.18
    hesis
    -2.18
    POSITIVE LOGITS
     town
    7.06
    Town
    6.63
     Town
    6.42
     towns
    5.69
    town
    5.31
     Towns
    5.23
     township
    4.77
     village
    4.22
    Vill
    3.91
     municipality
    3.61
    Activations Density 0.065%

    No Known Activations