© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 22941
    Prev
    Next
    INDEX
    Explanations

    specific information about mobile devices, particularly related to their specifications and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.15
    1:0.06
    2:0.09
    3:0.07
    4:0.05
    5:0.02
    6:0.09
    7:0.16
    8:0.02
    9:0.05
    10:0.11
    11:0.08
    Negative Logits
    pillar
    -2.84
     Hitchcock
    -2.68
    TPPStreamerBot
    -2.66
     Petroleum
    -2.30
     alcoholism
    -2.27
     hydra
    -2.27
     Manit
    -2.25
     horizont
    -2.25
     paintings
    -2.24
    thouse
    -2.21
    POSITIVE LOGITS
     SIM
    5.67
    SIM
    4.63
     prepaid
    3.33
     CHO
    3.08
     LTE
    3.07
     WhatsApp
    3.03
     warr
    2.78
     SMS
    2.72
     WiFi
    2.69
    Hong
    2.69
    Activations Density 0.001%

    No Known Activations