© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-ATT-KK
    11. 43879
    Prev
    Next
    INDEX
    Explanations

    expressions related to navigation and positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.08
    3:0.06
    4:0.05
    5:0.03
    6:0.42
    7:0.05
    8:0.05
    9:0.06
    10:0.09
    11:0.03
    Negative Logits
    PB
    -1.27
     {:
    -1.24
     Chains
    -1.22
     safely
    -1.22
    イト
    -1.21
     effortlessly
    -1.19
    [/
    -1.17
     [|
    -1.16
    ulnerability
    -1.14
    imar
    -1.12
    POSITIVE LOGITS
     ears
    1.26
    sed
    1.26
     Hispan
    1.26
     drawer
    1.22
    translation
    1.20
     wiser
    1.20
     Kessler
    1.18
     foil
    1.17
     Rowling
    1.13
    ritten
    1.11
    Activations Density 0.233%

    No Known Activations