© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22039
    Prev
    Next
    INDEX
    Explanations

    words related to products and their features

    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
    1:0.03
    2:0.11
    3:0.09
    4:0.06
    5:0.14
    6:0.09
    7:0.05
    8:0.09
    9:0.09
    10:0.11
    11:0.03
    Negative Logits
     mediation
    -1.16
     tut
    -1.07
     downstream
    -1.06
     Entered
    -1.04
     frivol
    -1.00
     Investig
    -0.98
     surrog
    -0.98
     unanim
    -0.97
     ba
    -0.96
     alleg
    -0.96
    POSITIVE LOGITS
    malink
    1.24
     (?,
    1.23
    atus
    1.18
    ovie
    1.15
    MSN
    1.13
    orea
    1.10
    Topics
    1.10
     Featuring
    1.09
    III
    1.08
    unker
    1.08
    Activations Density 0.448%

    No Known Activations