© 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. 3-ATT-KK
    11. 13605
    Prev
    Next
    INDEX
    Explanations

    terms related to legal processes and criminal incidents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases indicating previous actions or states, particularly those that are ongoing or have not been completed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.03
    2:0.17
    3:0.06
    4:0.01
    5:0.03
    6:0.06
    7:0.04
    8:0.08
    9:0.12
    10:0.14
    11:0.18
    Negative Logits
     Jackets
    -0.97
    Net
    -0.93
    ception
    -0.92
    park
    -0.90
    lies
    -0.89
    *)
    -0.79
    assic
    -0.79
     nuts
    -0.75
    poses
    -0.74
     Harding
    -0.74
    POSITIVE LOGITS
     nor
    1.39
     anymore
    1.26
    yet
    1.17
     yet
    1.07
    Nor
    0.98
     whatsoever
    0.94
     definitively
    0.89
     distinction
    0.87
     satisf
    0.86
     unamb
    0.86
    Activations Density 0.046%

    No Known Activations