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. 9-ATT-KK
    6. 18724
    Prev
    Next
    INDEX
    Explanations

    names of places and people

    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
    1:0.04
    2:0.05
    3:0.06
    4:0.03
    5:0.05
    6:0.21
    7:0.03
    8:0.04
    9:0.35
    10:0.04
    11:0.02
    Negative Logits
     piping
    -4.02
     Jaune
    -3.59
     Isis
    -3.57
     Pyrrha
    -3.54
     Hydra
    -3.30
     Pipe
    -3.25
    pipe
    -3.24
     pipes
    -3.23
    Ja
    -3.21
     PJ
    -3.15
    POSITIVE LOGITS
    land
    5.92
    lander
    5.11
    LAND
    5.05
    Land
    4.89
     Land
    4.67
    lands
    4.40
    landers
    4.39
    eland
    4.33
    ld
    4.19
     Vand
    3.95
    Activations Density 0.001%

    No Known Activations