© 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. 2-ATT-KK
    11. 22594
    Prev
    Next
    INDEX
    Explanations

    locations and names that contain the substring "Nav"

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

    words related to navigational and directional themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.03
    2:0.28
    3:0.07
    4:0.15
    5:0.06
    6:0.03
    7:0.02
    8:0.05
    9:0.10
    10:0.06
    11:0.03
    Negative Logits
     glim
    -1.45
     conflic
    -1.31
     cannibal
    -1.31
     spor
    -1.28
     gobl
    -1.28
     hindsight
    -1.25
     cass
    -1.23
     ransom
    -1.23
     overc
    -1.18
     Winc
    -1.17
    POSITIVE LOGITS
    Center
    1.43
    ALS
    1.40
    als
    1.31
    Services
    1.27
    orthy
    1.25
    ATIONAL
    1.20
    itives
    1.19
    aternity
    1.18
    ById
    1.17
    uve
    1.16
    Activations Density 0.003%

    No Known Activations