© 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. 3-ATT-KK
    11. 8180
    Prev
    Next
    INDEX
    Explanations

    instances of the word "it" and phrases associated with escape or getting out

    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
    0:0.01
    1:0.02
    2:0.15
    3:0.23
    4:0.01
    5:0.01
    6:0.06
    7:0.10
    8:0.08
    9:0.18
    10:0.05
    11:0.04
    Negative Logits
     Methods
    -1.31
     corrid
    -1.17
    Area
    -1.04
    eatures
    -1.03
     apartheid
    -1.01
     Carney
    -1.01
    Method
    -0.97
    LOAD
    -0.95
     Bots
    -0.93
     Areas
    -0.93
    POSITIVE LOGITS
    retty
    1.55
    ocobo
    1.45
    chy
    1.31
    osate
    1.22
     traction
    1.14
    ��
    1.12
    patrick
    1.10
    ticket
    1.10
     derailed
    1.08
    uable
    1.05
    Activations Density 0.163%

    No Known Activations