© 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. 22110
    Prev
    Next
    INDEX
    Explanations

    strings of characters that indicate social media engagement

    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
    2:0.11
    3:0.14
    4:0.03
    5:0.08
    6:0.09
    7:0.05
    8:0.10
    9:0.08
    10:0.13
    11:0.06
    Negative Logits
    CLASSIFIED
    -1.11
    illary
    -1.07
    ESCO
    -1.04
    hered
    -1.03
    ▬
    -1.01
     respectively
    -0.98
     gradient
    -0.97
     unison
    -0.97
    Saharan
    -0.94
    taboola
    -0.94
    POSITIVE LOGITS
    rez
    1.30
    dyl
    1.28
    olor
    1.24
    oston
    1.23
    ayn
    1.22
    Uk
    1.21
    _-_
    1.15
    __
    1.14
    imon
    1.13
    amas
    1.13
    Activations Density 0.042%

    No Known Activations