© 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. 14533
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events that prompt a specific response or change from a person or organization, often including specific instructions or outcomes

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.10
    1:0.03
    2:0.16
    3:0.11
    4:0.08
    5:0.13
    6:0.04
    7:0.03
    8:0.14
    9:0.06
    10:0.04
    11:0.02
    Negative Logits
     BMC
    -1.20
     Ahead
    -1.11
     ahead
    -1.09
     sucks
    -1.08
    wine
    -1.07
    Els
    -1.07
     Unloaded
    -1.06
     Elon
    -1.05
     DV
    -1.05
     Chevy
    -1.05
    POSITIVE LOGITS
     occasions
    1.48
     arrival
    1.35
     occasion
    1.32
     expiration
    1.22
     shores
    1.20
     outset
    1.19
    覚醒
    1.18
    rocal
    1.15
     premise
    1.14
     Formation
    1.11
    Activations Density 0.026%

    No Known Activations