© 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. 22157
    Prev
    Next
    INDEX
    Explanations

    when the term "need" and its variations are used in the context of obligations or requirements

    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
    2:0.06
    3:0.04
    4:0.09
    5:0.06
    6:0.04
    7:0.10
    8:0.18
    9:0.06
    10:0.15
    11:0.08
    Negative Logits
    aroo
    -1.26
    ARC
    -1.03
    Journal
    -1.02
    furt
    -1.01
    ccording
    -0.99
    ��
    -0.97
    %"
    -0.95
    indle
    -0.93
     miscarriage
    -0.91
    ��
    -0.91
    POSITIVE LOGITS
     upkeep
    1.23
     brakes
    1.11
     perman
    1.09
     expertise
    1.04
     ASAP
    1.03
     urgently
    1.02
     upgrade
    0.97
     rethink
    0.96
     verification
    0.93
     patience
    0.91
    Activations Density 0.152%

    No Known Activations