© 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. 2-ATT-KK
    11. 13679
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ed' or 'ing', or locations/times like 'gate' or 'on'

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.06
    1:0.01
    2:0.32
    3:0.04
    4:0.06
    5:0.06
    6:0.01
    7:0.06
    8:0.08
    9:0.05
    10:0.12
    11:0.06
    Negative Logits
    ancial
    -1.56
    cellence
    -1.39
    osate
    -1.35
    icion
    -1.30
    minster
    -1.27
    atomic
    -1.25
    iard
    -1.25
    Reviewed
    -1.22
    cest
    -1.18
    Anne
    -1.16
    POSITIVE LOGITS
     wrinkles
    1.12
     pregn
    1.11
     phases
    1.11
    =\"
    1.10
     Kraken
    1.07
     bases
    1.06
     Halls
    1.05
     lessons
    1.04
     basics
    1.04
     \"
    1.02
    Activations Density 0.111%

    No Known Activations