© 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. 3-ATT-KK
    11. 14018
    Prev
    Next
    INDEX
    Explanations

    descriptions of progress or state of a situation, with the presence of comparisons or evaluations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    adjectives that indicate nuances of quality or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.03
    2:0.13
    3:0.08
    4:0.01
    5:0.03
    6:0.14
    7:0.06
    8:0.05
    9:0.04
    10:0.07
    11:0.28
    Negative Logits
     certific
    -1.27
    uments
    -1.23
    iership
    -1.14
    YES
    -1.13
    ousands
    -1.06
     Ys
    -1.02
     routinely
    -0.99
    ��
    -0.99
     iPads
    -0.97
     EVERY
    -0.97
    POSITIVE LOGITS
    icho
    1.23
    nered
    1.22
    cific
    1.13
    neck
    1.10
    auld
    1.09
    atto
    1.07
     leaning
    1.07
    ussian
    1.07
    legged
    1.04
    iatus
    1.04
    Activations Density 0.008%

    No Known Activations