© 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. 22118
    Prev
    Next
    INDEX
    Explanations

    phrases that use the words "essentially" and "basically" to describe concepts or qualities

    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
    0:0.16
    1:0.03
    2:0.11
    3:0.10
    4:0.15
    5:0.07
    6:0.04
    7:0.02
    8:0.08
    9:0.11
    10:0.05
    11:0.02
    Negative Logits
     analyst
    -1.24
     promptly
    -1.22
     swiftly
    -1.22
     reportedly
    -1.20
     urgently
    -1.20
     Insight
    -1.19
     visibly
    -1.19
    andra
    -1.10
     ®
    -1.10
    alty
    -1.09
    POSITIVE LOGITS
    roman
    1.39
    utical
    1.35
    \\\\\\\\
    1.28
    gebra
    1.27
    SpaceEngineers
    1.25
    Fuck
    1.23
    anut
    1.19
     rewriting
    1.18
     wast
    1.15
     dudes
    1.15
    Activations Density 0.026%

    No Known Activations