© 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. 22644
    Prev
    Next
    INDEX
    Explanations

    complementary elements or features within a larger system

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

    phrases related to support and enhancement of various elements or concepts

    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
    2:0.15
    3:0.07
    4:0.14
    5:0.09
    6:0.03
    7:0.02
    8:0.16
    9:0.13
    10:0.06
    11:0.02
    Negative Logits
    schild
    -1.25
    iae
    -1.22
     Accessed
    -1.15
    pload
    -1.12
     hanged
    -1.10
     Reporter
    -1.09
    opol
    -1.07
     ______
    -1.06
     hijacked
    -1.05
    pit
    -1.05
    POSITIVE LOGITS
     charm
    1.39
     precon
    1.38
     lineup
    1.36
    rices
    1.33
     selections
    1.33
    ietal
    1.27
     seasons
    1.25
    ainment
    1.23
     groundwork
    1.22
     complement
    1.22
    Activations Density 0.006%

    No Known Activations