© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22909
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and political efforts

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

    phrases indicating efforts, objectives, or actions directed towards a goal

    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
    0:0.04
    1:0.02
    2:0.09
    3:0.03
    4:0.35
    5:0.08
    6:0.03
    7:0.02
    8:0.07
    9:0.14
    10:0.05
    11:0.02
    Negative Logits
    Flo
    -1.52
     Reserved
    -1.47
     NCT
    -1.41
     Sins
    -1.38
    �
    -1.37
     Flo
    -1.37
    BB
    -1.35
    country
    -1.34
     Reasons
    -1.33
    arant
    -1.32
    POSITIVE LOGITS
     compromise
    1.56
     resolving
    1.51
    issance
    1.50
     conduc
    1.50
     cram
    1.47
     scrimmage
    1.47
     renov
    1.46
     resolve
    1.46
     overturn
    1.46
     totality
    1.44
    Activations Density 0.019%

    No Known Activations