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. 2968
    Prev
    Next
    INDEX
    Explanations

    connector phrases and transitional words that link ideas together

    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
    2:0.12
    3:0.07
    4:0.15
    5:0.02
    6:0.34
    7:0.05
    8:0.03
    9:0.02
    10:0.06
    11:0.05
    Negative Logits
    ican
    -1.48
    ��
    -1.36
    ��
    -1.28
     Axis
    -1.26
     Registry
    -1.24
    Sax
    -1.14
    lite
    -1.13
    llan
    -1.13
     Indies
    -1.12
    ゴン
    -1.10
    POSITIVE LOGITS
    AMY
    1.28
    ansky
    1.22
    NetMessage
    1.21
    ITH
    1.18
     exponential
    1.16
    eki
    1.14
     bullish
    1.13
     ETH
    1.12
    uberty
    1.10
    idious
    1.10
    Activations Density 0.079%

    No Known Activations