© 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. 36054
    Prev
    Next
    INDEX
    Explanations

    references to openings, whether physical or metaphorical

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    2:0.09
    3:0.06
    4:0.35
    5:0.03
    6:0.04
    7:0.16
    8:0.03
    9:0.04
    10:0.06
    11:0.06
    Negative Logits
    clusive
    -1.38
    ighter
    -1.33
     Donation
    -1.29
    imum
    -1.25
    ogue
    -1.25
     guiActiveUnfocused
    -1.23
    owl
    -1.23
     Away
    -1.22
     Lub
    -1.22
     ape
    -1.21
    POSITIVE LOGITS
    ricanes
    1.59
     loopholes
    1.46
     portals
    1.44
     temptation
    1.41
     flood
    1.40
     titan
    1.31
     duct
    1.30
     hydra
    1.29
    roxy
    1.28
    cknow
    1.27
    Activations Density 0.004%

    No Known Activations