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. 5-ATT-KK
    6. 19137
    Prev
    Next
    INDEX
    Explanations

    gerund forms of verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.02
    2:0.13
    3:0.07
    4:0.07
    5:0.03
    6:0.18
    7:0.15
    8:0.04
    9:0.05
    10:0.08
    11:0.08
    Negative Logits
     binding
    -1.36
     replay
    -1.33
     ensured
    -1.30
    witch
    -1.30
     rele
    -1.28
    answered
    -1.25
    kit
    -1.23
    together
    -1.23
     ensuring
    -1.22
    Nap
    -1.22
    POSITIVE LOGITS
     Diseases
    1.60
    Merit
    1.51
    EStreamFrame
    1.46
    essim
    1.44
     Flower
    1.42
    ��
    1.41
     Growth
    1.40
     Decay
    1.36
     Distribut
    1.36
    culosis
    1.35
    Activations Density 0.000%

    No Known Activations