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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 28074
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical data, particularly in a list or tabular format

    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
    0:0.04
    1:0.02
    2:0.05
    3:0.05
    4:0.06
    5:0.03
    6:0.43
    7:0.05
    8:0.04
    9:0.05
    10:0.07
    11:0.05
    Negative Logits
    isha
    -1.52
    isexual
    -1.34
    ocene
    -1.32
     brushing
    -1.30
    ollah
    -1.28
     misconception
    -1.26
    uments
    -1.24
     ignorance
    -1.21
    aimon
    -1.20
    anan
    -1.20
    POSITIVE LOGITS
    msg
    1.54
    percent
    1.44
    ּ
    1.31
    616
    1.30
     Ct
    1.27
     Expend
    1.27
     Typh
    1.25
    Ct
    1.24
    �
    1.24
    855
    1.22
    Activations Density 0.059%

    No Known Activations