© 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. 42926
    Prev
    Next
    INDEX
    Explanations

    common conjunctions and auxiliary verbs used to connect phrases and clauses in sentences

    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
    0:0.03
    1:0.02
    2:0.05
    3:0.12
    4:0.10
    5:0.07
    6:0.23
    7:0.03
    8:0.06
    9:0.11
    10:0.08
    11:0.04
    Negative Logits
    FTWARE
    -1.32
     corrid
    -1.22
    psey
    -1.21
    berus
    -1.20
    anche
    -1.18
    ..............
    -1.16
     Tec
    -1.12
     Earthqu
    -1.12
    riott
    -1.11
     Crescent
    -1.09
    POSITIVE LOGITS
     doesnt
    1.53
     didnt
    1.48
    english
    1.40
    entious
    1.22
     wont
    1.20
    ids
    1.19
    ergic
    1.18
     lacks
    1.15
     nailed
    1.14
    bek
    1.13
    Activations Density 0.059%

    No Known Activations