© 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. 9-ATT-KK
    11. 17443
    Prev
    Next
    INDEX
    Explanations

    indicators of online interactions, particularly social media context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.23
    2:0.07
    3:0.05
    4:0.12
    5:0.07
    6:0.04
    7:0.10
    8:0.04
    9:0.05
    10:0.06
    11:0.07
    Negative Logits
    ghai
    -2.50
    prise
    -2.44
    ilar
    -2.37
    oming
    -2.36
    ilitating
    -2.28
    lime
    -2.25
     enraged
    -2.24
     newfound
    -2.23
    ellow
    -2.21
    lling
    -2.19
    POSITIVE LOGITS
    there
    4.45
     there
    4.36
    There
    4.17
     THERE
    3.56
     There
    3.55
    魔
    3.07
    �
    2.91
    テ
    2.68
     �
    2.62
     anywhere
    2.61
    Activations Density 0.057%

    No Known Activations