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. 5-ATT-KK
    6. 7399
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "convene" and its variations in context, particularly related to meetings or gatherings

    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
    0:0.02
    1:0.01
    2:0.05
    3:0.06
    4:0.14
    5:0.03
    6:0.05
    7:0.36
    8:0.03
    9:0.04
    10:0.09
    11:0.07
    Negative Logits
     slope
    -1.66
    龍�
    -1.56
     distances
    -1.56
     aspire
    -1.55
     surfaces
    -1.53
     exposed
    -1.49
     perceive
    -1.49
     distance
    -1.46
    iour
    -1.46
    gey
    -1.45
    POSITIVE LOGITS
     consultations
    1.81
    rehensive
    1.78
    Discussion
    1.67
    Council
    1.66
     deliberations
    1.63
     discussion
    1.62
    Assembly
    1.60
    Effective
    1.57
     conference
    1.53
    semble
    1.53
    Activations Density 0.001%

    No Known Activations