© 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. 22166
    Prev
    Next
    INDEX
    Explanations

    instances of theft and burglary-related activities

    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
    0:0.02
    1:0.02
    2:0.05
    3:0.11
    4:0.09
    5:0.37
    6:0.01
    7:0.03
    8:0.03
    9:0.18
    10:0.01
    11:0.02
    Negative Logits
    .).
    -4.02
    .?
    -3.87
    .�
    -3.64
    .」
    -3.37
    _.
    -3.35
    .''
    -3.28
    .]
    -3.19
    .)
    -3.15
    .'
    -3.06
    .*
    -3.04
    POSITIVE LOGITS
     -
    2.88
     civilisation
    2.76
     whilst
    2.65
    isable
    2.60
     Nato
    2.50
     favourites
    2.48
     favourite
    2.47
     organising
    2.43
     including
    2.43
    alys
    2.42
    Activations Density 0.729%

    No Known Activations