© 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. 11990
    Prev
    Next
    INDEX
    Explanations

    phrases related to leadership, teamwork, and communication

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

    conversational phrases and expressions

    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
    1:0.06
    2:0.16
    3:0.02
    4:0.01
    5:0.02
    6:0.13
    7:0.10
    8:0.19
    9:0.14
    10:0.04
    11:0.08
    Negative Logits
    phabet
    -1.33
    ciation
    -1.18
     governs
    -1.16
     Paddock
    -1.15
     lasts
    -1.12
    webkit
    -1.11
     htt
    -1.07
     Kare
    -1.06
     comprises
    -1.06
     combines
    -1.05
    POSITIVE LOGITS
    erest
    1.55
    ivable
    1.52
    done
    1.44
    uble
    1.42
     suspic
    1.35
    ocent
    1.31
    inently
    1.28
    ueless
    1.28
    ulnerable
    1.26
    duc
    1.25
    Activations Density 0.043%

    No Known Activations