© 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. 13930
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions, decisions, or statements made by people

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

    verbs and phrases indicating descriptions and ongoing actions involving individuals and their states

    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
    0:0.08
    1:0.06
    2:0.05
    3:0.02
    4:0.34
    5:0.06
    6:0.07
    7:0.05
    8:0.05
    9:0.05
    10:0.07
    11:0.05
    Negative Logits
    dq
    -1.75
     canvas
    -1.74
     viz
    -1.62
     Combine
    -1.61
    roman
    -1.57
    ��
    -1.57
    rolet
    -1.56
     palette
    -1.52
     couch
    -1.51
     combine
    -1.49
    POSITIVE LOGITS
    mania
    1.86
    Fast
    1.78
    Reviewer
    1.74
    gam
    1.67
    venants
    1.61
    bol
    1.59
    :'
    1.58
    Attempts
    1.57
    abilia
    1.57
     accused
    1.55
    Activations Density 0.203%

    No Known Activations