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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 7816
    Prev
    Next
    INDEX
    Explanations

    key phrases and sentences that indicate important assumptions, decisions, or actions within governance and political contexts

    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
    0:0.02
    1:0.12
    2:0.08
    3:0.04
    4:0.03
    5:0.09
    6:0.08
    7:0.08
    8:0.22
    9:0.04
    10:0.07
    11:0.06
    Negative Logits
    ecycle
    -1.46
    assic
    -1.42
    utterstock
    -1.41
    quart
    -1.38
    bowl
    -1.30
    ciation
    -1.28
    plet
    -1.24
    }.
    -1.24
    .�
    -1.22
    etimes
    -1.21
    POSITIVE LOGITS
     "#
    1.58
     "…
    1.44
    Dear
    1.33
     Dear
    1.30
    olicited
    1.26
     "...
    1.26
     "'
    1.21
    Warning
    1.17
    RM
    1.16
    Congratulations
    1.16
    Activations Density 0.153%

    No Known Activations