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. 13723
    Prev
    Next
    INDEX
    Explanations

    numerical or technical information

    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
    0:0.06
    1:0.02
    2:0.07
    3:0.15
    4:0.04
    5:0.09
    6:0.08
    7:0.08
    8:0.05
    9:0.09
    10:0.14
    11:0.07
    Negative Logits
    ADRA
    -1.20
    NetMessage
    -1.18
    renheit
    -1.05
    黒
    -0.96
     Canaveral
    -0.96
     srf
    -0.96
    terday
    -0.94
     weddings
    -0.94
    edIn
    -0.94
    ��
    -0.94
    POSITIVE LOGITS
    iest
    1.62
    liest
    1.49
    hest
    1.31
    osphere
    1.31
    est
    1.18
     portion
    1.18
    most
    1.15
    cients
    1.10
    erest
    1.09
     thing
    1.08
    Activations Density 0.676%

    No Known Activations