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. 19398
    Prev
    Next
    INDEX
    Explanations

    structured data related to SCP (Secure, Contain, Protect) entities

    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
    0:0.03
    1:0.03
    2:0.08
    3:0.13
    4:0.08
    5:0.04
    6:0.06
    7:0.15
    8:0.15
    9:0.05
    10:0.10
    11:0.05
    Negative Logits
     Jama
    -1.71
    oğ
    -1.61
    icka
    -1.52
    alach
    -1.51
    osi
    -1.51
     territ
    -1.47
    wana
    -1.46
     psy
    -1.46
     anecd
    -1.45
    WS
    -1.44
    POSITIVE LOGITS
    geries
    1.85
    ERY
    1.57
     suitcase
    1.55
     correction
    1.38
     haste
    1.37
     bearing
    1.37
    �士
    1.36
    agog
    1.35
     captivity
    1.34
     disposition
    1.34
    Activations Density 0.000%

    No Known Activations