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. 7-ATT-KK
    6. 18906
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters

    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
    0:0.05
    1:0.07
    2:0.22
    3:0.06
    4:0.03
    5:0.03
    6:0.05
    7:0.04
    8:0.04
    9:0.09
    10:0.24
    11:0.03
    Negative Logits
     decor
    -2.17
     mathemat
    -2.03
     flavored
    -2.00
     physic
    -1.96
     dram
    -1.94
     cutter
    -1.92
    mist
    -1.90
    >:
    -1.89
     Bot
    -1.88
     mechanic
    -1.86
    POSITIVE LOGITS
    AFP
    3.85
     AFP
    3.23
    Que
    2.31
     Kau
    2.31
    プ
    2.25
    deen
    2.25
    nai
    2.25
    ati
    2.24
    Elsa
    2.23
    Union
    2.23
    Activations Density 0.000%

    No Known Activations