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. 7-ATT-KK
    6. 9194
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to rules, regulations, and documentation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    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
    1:0.06
    2:0.40
    3:0.05
    4:0.02
    5:0.03
    6:0.03
    7:0.08
    8:0.04
    9:0.05
    10:0.11
    11:0.03
    Negative Logits
     jokes
    -2.81
     joke
    -2.57
     laughter
    -2.56
     crap
    -2.42
     nightmares
    -2.37
     laughs
    -2.32
     cartoons
    -2.25
     goof
    -2.24
     laughing
    -2.23
     boiled
    -2.23
    POSITIVE LOGITS
     enroll
    2.77
     establish
    2.77
     enact
    2.76
    ablish
    2.72
    intendent
    2.71
     perform
    2.69
    establish
    2.62
    execute
    2.59
     undertake
    2.58
     equip
    2.56
    Activations Density 0.045%

    No Known Activations