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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 13892
    Prev
    Next
    INDEX
    Explanations

    words related to long-term planning and objectives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.03
    2:0.15
    3:0.05
    4:0.36
    5:0.05
    6:0.02
    7:0.03
    8:0.04
    9:0.09
    10:0.04
    11:0.02
    Negative Logits
    ogly
    -1.47
     Steal
    -1.45
     Holiday
    -1.38
    kind
    -1.36
    anan
    -1.28
    along
    -1.28
    CHA
    -1.27
     gal
    -1.25
    aldi
    -1.25
    Dub
    -1.24
    POSITIVE LOGITS
    iatus
    1.87
    cale
    1.66
    than
    1.63
    ]}
    1.40
    urations
    1.39
    �
    1.33
    ppo
    1.29
     toler
    1.27
    itus
    1.27
    stable
    1.27
    Activations Density 0.006%

    No Known Activations