© 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. 9-ATT-KK
    6. 2973
    Prev
    Next
    INDEX
    Explanations

    key concepts related to demographics and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.02
    2:0.04
    3:0.33
    4:0.04
    5:0.06
    6:0.03
    7:0.03
    8:0.04
    9:0.03
    10:0.25
    11:0.03
    Negative Logits
     heirs
    -1.75
     permanently
    -1.70
     technicians
    -1.70
     FEMA
    -1.68
    ��極
    -1.67
     contractors
    -1.66
    Companies
    -1.66
     royalties
    -1.64
     Engineers
    -1.63
     agents
    -1.63
    POSITIVE LOGITS
    uesday
    3.01
    nesday
    2.88
    topic
    2.72
    ursday
    2.63
    onday
    2.49
    aturday
    2.47
    ndum
    2.25
     Topic
    2.17
     topic
    2.07
     behalf
    2.05
    Activations Density 0.062%

    No Known Activations