Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 13720
    Prev
    Next
    INDEX
    Explanations

    special characters and programming-related terms

    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
    0:0.08
    1:0.05
    2:0.12
    3:0.14
    4:0.05
    5:0.18
    6:0.05
    7:0.03
    8:0.09
    9:0.07
    10:0.07
    11:0.03
    Negative Logits
    ���
    -1.28
    phrine
    -1.14
    aration
    -1.12
    achev
    -1.12
    hement
    -1.08
     aggrav
    -1.05
    arations
    -1.03
    ilar
    -1.02
    nings
    -1.02
     condem
    -1.02
    POSITIVE LOGITS
     Morph
    1.15
    Ti
    1.13
     Comput
    1.09
    ='
    1.06
     tun
    1.05
    lik
    1.04
     nu
    1.03
    Param
    1.01
     Debor
    1.01
    Meg
    1.01
    Activations Density 0.006%

    No Known Activations