© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 23324
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to technical features or settings

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

    phrases indicating wide-ranging or expansive 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
    0:0.04
    1:0.03
    2:0.33
    3:0.05
    4:0.25
    5:0.04
    6:0.03
    7:0.01
    8:0.04
    9:0.06
    10:0.05
    11:0.02
    Negative Logits
    CHA
    -1.39
    _-
    -1.37
     behav
    -1.35
    ���
    -1.32
    minus
    -1.29
    ּ
    -1.22
     CLS
    -1.15
    raped
    -1.14
     propos
    -1.14
    displayText
    -1.11
    POSITIVE LOGITS
    ]}
    1.60
    interstitial
    1.39
    ortment
    1.37
    atoes
    1.31
    Thumbnail
    1.28
    comed
    1.26
    aminer
    1.26
    annels
    1.26
    angle
    1.25
    circ
    1.25
    Activations Density 0.007%

    No Known Activations