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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22088
    Prev
    Next
    INDEX
    Explanations

    numbers and positive performance metrics related to technology

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.09
    1:0.05
    2:0.09
    3:0.08
    4:0.08
    5:0.11
    6:0.04
    7:0.03
    8:0.08
    9:0.17
    10:0.10
    11:0.03
    Negative Logits
    >:
    -1.42
     Haitian
    -1.42
    hun
    -1.37
    rh
    -1.31
     Betsy
    -1.23
     bere
    -1.21
    ricia
    -1.21
    skip
    -1.17
     Valerie
    -1.16
    jured
    -1.15
    POSITIVE LOGITS
     routers
    1.45
     Commando
    1.35
    EVA
    1.35
     photons
    1.33
     Router
    1.33
     tyres
    1.28
     efficiently
    1.28
     atoms
    1.25
     OLED
    1.24
    AX
    1.24
    Activations Density 0.047%

    No Known Activations