Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20669
    Prev
    Next
    INDEX
    Explanations

    phrases related to resource management and planning

    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
    2:0.06
    3:0.18
    4:0.03
    5:0.07
    6:0.02
    7:0.06
    8:0.02
    9:0.01
    10:0.38
    11:0.04
    Negative Logits
     unintentional
    -2.63
    Topic
    -2.33
     incorrectly
    -2.30
     mockery
    -2.28
     errone
    -2.17
     unintentionally
    -2.15
     ridicule
    -2.08
    ーク
    -2.02
    )</
    -1.96
     harshly
    -1.94
    POSITIVE LOGITS
     capable
    3.50
     sufficient
    3.43
     enough
    3.17
     available
    3.17
     ready
    3.15
     suitable
    3.08
     ample
    2.99
     adequate
    2.96
    enough
    2.95
     reliable
    2.91
    Activations Density 0.739%

    No Known Activations