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. 43507
    Prev
    Next
    INDEX
    Explanations

    mouse-related interactions and actions

    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
    0:0.03
    1:0.01
    2:0.06
    3:0.04
    4:0.06
    5:0.04
    6:0.28
    7:0.10
    8:0.04
    9:0.03
    10:0.14
    11:0.10
    Negative Logits
     Loch
    -1.27
     Akin
    -1.25
     Oral
    -1.18
     Lauder
    -1.18
     Letters
    -1.15
     adj
    -1.13
     oath
    -1.12
     oral
    -1.11
    estic
    -1.10
    ilet
    -1.10
    POSITIVE LOGITS
    rocket
    1.36
    merce
    1.29
    itans
    1.20
    EStream
    1.19
    inez
    1.18
    lag
    1.18
    etc
    1.15
    tainment
    1.12
    izons
    1.11
    hunt
    1.10
    Activations Density 0.001%

    No Known Activations