© 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. 22044
    Prev
    Next
    INDEX
    Explanations

    prepositions and their usage in various contexts

    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
    1:0.02
    2:0.11
    3:0.09
    4:0.04
    5:0.13
    6:0.04
    7:0.07
    8:0.07
    9:0.13
    10:0.14
    11:0.05
    Negative Logits
    etheless
    -1.36
     difference
    -1.28
     wise
    -1.24
     tolerated
    -1.18
    hetically
    -1.12
    wise
    -1.10
    abyte
    -1.04
     exerted
    -1.04
     endif
    -1.03
    ensibly
    -1.01
    POSITIVE LOGITS
     Kills
    1.24
    esm
    1.14
     Brewery
    1.08
    isons
    1.08
    Vert
    1.08
     Zeit
    1.07
    bats
    1.06
     Dek
    1.05
     Tours
    1.05
     Attacks
    1.04
    Activations Density 0.204%

    No Known Activations