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

    Neuronpedia

    Jacobian LensNEW
    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. 42310
    Prev
    Next
    INDEX
    Explanations

    instances of notable actions or positions in various contexts

    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
    0:0.02
    1:0.02
    2:0.16
    3:0.08
    4:0.12
    5:0.02
    6:0.30
    7:0.03
    8:0.04
    9:0.03
    10:0.10
    11:0.05
    Negative Logits
     intersections
    -1.55
    gradient
    -1.54
    brance
    -1.38
    Sport
    -1.35
     EVs
    -1.27
    urations
    -1.27
     translations
    -1.21
     paths
    -1.21
     progress
    -1.20
     transitions
    -1.18
    POSITIVE LOGITS
    etheless
    1.67
    together
    1.64
    uph
    1.36
    whose
    1.32
    ��
    1.31
    �士
    1.25
    ni
    1.24
    ensis
    1.23
    Together
    1.22
    called
    1.21
    Activations Density 0.136%

    No Known Activations