© 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. 22129
    Prev
    Next
    INDEX
    Explanations

    instances of the word "consider" and related discussions on options and evaluations

    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
    0:0.09
    1:0.03
    2:0.06
    3:0.10
    4:0.03
    5:0.09
    6:0.04
    7:0.02
    8:0.31
    9:0.06
    10:0.09
    11:0.03
    Negative Logits
    ufact
    -1.45
    ovember
    -1.36
    hesda
    -1.32
    ylan
    -1.23
     spew
    -1.15
    eps
    -1.10
    nesday
    -1.09
     Syl
    -1.07
    umps
    -1.07
     airst
    -1.07
    POSITIVE LOGITS
    ilitarian
    1.36
     favorably
    1.18
    adiq
    1.17
    NetMessage
    1.12
     Effective
    1.11
     deserving
    1.10
     objectively
    1.10
    humane
    1.08
    zu
    1.07
     TAMADRA
    1.06
    Activations Density 0.048%

    No Known Activations