© 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. 3-ATT-KK
    11. 7515
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or intent related to personal aspirations or goals

    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
    0:0.01
    1:0.03
    2:0.05
    3:0.20
    4:0.02
    5:0.03
    6:0.05
    7:0.15
    8:0.07
    9:0.18
    10:0.08
    11:0.07
    Negative Logits
    abase
    -1.22
    lang
    -1.08
    edin
    -1.08
    heet
    -1.03
     Laf
    -1.02
    hari
    -1.01
    claimer
    -0.99
    batch
    -0.98
    conference
    -0.98
     guiActiveUn
    -0.98
    POSITIVE LOGITS
     ali
    1.26
     openness
    1.22
     fidelity
    1.17
     individuality
    1.15
    venge
    1.11
     realism
    1.11
     uniqueness
    1.11
     mascul
    1.11
     exclus
    1.10
     companions
    1.10
    Activations Density 0.009%

    No Known Activations