© 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. 3-ATT-KK
    11. 13943
    Prev
    Next
    INDEX
    Explanations

    gestures or actions related to communication or affirmation

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

    phrases that express gestures or symbolic actions within a broader context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.07
    3:0.19
    4:0.02
    5:0.02
    6:0.12
    7:0.21
    8:0.05
    9:0.05
    10:0.08
    11:0.08
    Negative Logits
     Despair
    -1.17
     Exam
    -1.16
     coli
    -1.14
     pestic
    -1.11
     microbi
    -1.11
     Tests
    -1.11
     tuberculosis
    -1.10
     fumes
    -1.10
     archae
    -1.09
     contaminated
    -1.08
    POSITIVE LOGITS
    Accept
    1.24
    Lat
    1.23
    Norm
    1.20
     gesture
    1.12
    IAS
    1.11
    ihad
    1.11
     gestures
    1.09
    Moon
    1.09
    Position
    1.07
    imize
    1.07
    Activations Density 0.005%

    No Known Activations