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. 43455
    Prev
    Next
    INDEX
    Explanations

    mentions of formal events and press conferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.01
    1:0.01
    2:0.14
    3:0.16
    4:0.12
    5:0.03
    6:0.03
    7:0.09
    8:0.05
    9:0.04
    10:0.14
    11:0.13
    Negative Logits
    Interstitial
    -1.33
     Zy
    -1.31
    iate
    -1.30
     FAR
    -1.29
    hovah
    -1.27
     deregulation
    -1.23
    ACP
    -1.20
     lied
    -1.19
    ngth
    -1.18
     prev
    -1.18
    POSITIVE LOGITS
    aturdays
    1.44
    ruby
    1.39
     Salmon
    1.28
    panel
    1.22
    oland
    1.22
    ilst
    1.22
    pak
    1.19
     Reporter
    1.19
    omen
    1.18
     Tess
    1.17
    Activations Density 0.034%

    No Known Activations