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. 9-ATT-KK
    6. 165
    Prev
    Next
    INDEX
    Explanations

    references to influential political figures and their actions or characteristics

    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
    0:0.06
    1:0.02
    2:0.07
    3:0.04
    4:0.05
    5:0.04
    6:0.19
    7:0.06
    8:0.12
    9:0.20
    10:0.02
    11:0.06
    Negative Logits
     Bris
    -4.18
     Bans
    -3.82
     licences
    -3.79
     licence
    -3.78
     Isis
    -3.44
    Spect
    -3.35
     SQ
    -3.27
     kilometres
    -3.22
     Surviv
    -3.21
     Bac
    -3.19
    POSITIVE LOGITS
     Roosevelt
    10.35
     FDR
    7.84
     Roose
    6.24
     Theodore
    5.98
     Truman
    5.59
    odore
    5.25
    velt
    5.21
     Rudolph
    5.06
     Polo
    4.95
     Teddy
    4.93
    Activations Density 0.001%

    No Known Activations