© 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. 23031
    Prev
    Next
    INDEX
    Explanations

    reports, articles, descriptions or statements

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

    instances of published materials and associated actions, particularly reports and articles

    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
    0:0.06
    1:0.04
    2:0.05
    3:0.07
    4:0.05
    5:0.08
    6:0.05
    7:0.03
    8:0.33
    9:0.09
    10:0.06
    11:0.02
    Negative Logits
    gencies
    -1.31
    ealous
    -1.26
    connected
    -1.25
    chairs
    -1.19
    itect
    -1.18
    ahime
    -1.16
    idth
    -1.16
    iev
    -1.14
    stood
    -1.10
    orah
    -1.09
    POSITIVE LOGITS
    Edited
    1.39
     Gallup
    1.37
     corrid
    1.33
    folio
    1.32
    earable
    1.31
     Canaver
    1.29
     Gazette
    1.25
    summary
    1.20
    DragonMagazine
    1.20
    BuyableInstoreAndOnline
    1.18
    Activations Density 0.044%

    No Known Activations