© 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. 22600
    Prev
    Next
    INDEX
    Explanations

    mentions of social media usernames and handles

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

    mentions of social media accounts and interactions with them

    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
    0:0.17
    1:0.05
    2:0.07
    3:0.13
    4:0.04
    5:0.11
    6:0.07
    7:0.03
    8:0.11
    9:0.07
    10:0.07
    11:0.03
    Negative Logits
     ®
    -1.39
     virtues
    -1.30
     therein
    -1.29
     astronauts
    -1.26
     treasures
    -1.25
     arsenic
    -1.21
     pleasures
    -1.17
     Sodium
    -1.11
     fishes
    -1.11
    etheless
    -1.10
    POSITIVE LOGITS
    yp
    1.58
    union
    1.33
    riot
    1.29
    spr
    1.29
    record
    1.28
    oll
    1.26
    poll
    1.25
    nee
    1.24
    hz
    1.24
    gyn
    1.23
    Activations Density 0.019%

    No Known Activations