© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43830
    Prev
    Next
    INDEX
    Explanations

    expressions of knowledge and awareness

    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
    0:0.12
    1:0.12
    2:0.03
    3:0.04
    4:0.04
    5:0.22
    6:0.03
    7:0.03
    8:0.14
    9:0.07
    10:0.06
    11:0.05
    Negative Logits
     termination
    -1.55
     consolidation
    -1.54
     merging
    -1.53
     remaining
    -1.51
     terminating
    -1.46
     merger
    -1.40
     rollout
    -1.40
     failure
    -1.39
     collapsing
    -1.39
     continuation
    -1.37
    POSITIVE LOGITS
    ESSION
    1.48
    idian
    1.47
    TextColor
    1.45
    ��
    1.44
    OOD
    1.43
    hour
    1.42
    hours
    1.38
    Professor
    1.36
    mosp
    1.36
    GoldMagikarp
    1.34
    Activations Density 0.014%

    No Known Activations