© 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. 7366
    Prev
    Next
    INDEX
    Explanations

    references to authority and influence

    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
    0:0.03
    1:0.07
    2:0.14
    3:0.33
    4:0.03
    5:0.03
    6:0.09
    7:0.06
    8:0.04
    9:0.03
    10:0.06
    11:0.04
    Negative Logits
     misunderstanding
    -1.33
     Mellon
    -1.17
     unchecked
    -1.12
     Lanka
    -1.11
     servicing
    -1.09
     escalation
    -1.07
     uncontrolled
    -1.07
     avoidance
    -1.05
     captivity
    -1.05
     Viktor
    -1.04
    POSITIVE LOGITS
    CEO
    1.46
    20439
    1.43
    incial
    1.29
    rans
    1.27
    sure
    1.27
    ulhu
    1.25
    �
    1.24
     sidx
    1.24
    ️
    1.24
    vae
    1.23
    Activations Density 0.201%

    No Known Activations