© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 19860
    Prev
    Next
    INDEX
    Explanations

    phrases indicating legal or regulatory processes related to cases

    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
    0:0.02
    1:0.01
    2:0.35
    3:0.05
    4:0.06
    5:0.03
    6:0.10
    7:0.10
    8:0.09
    9:0.03
    10:0.05
    11:0.05
    Negative Logits
    irlf
    -2.10
    rote
    -2.02
    Prev
    -1.83
    affe
    -1.83
    arie
    -1.79
    Sah
    -1.72
    龍喚士
    -1.72
    nox
    -1.67
    cients
    -1.63
    龍契士
    -1.62
    POSITIVE LOGITS
     attributable
    1.68
    ciation
    1.65
     pairs
    1.59
     conceivable
    1.59
     collision
    1.57
     indicative
    1.57
     succession
    1.56
     absurdity
    1.56
     imaginable
    1.55
     convergence
    1.53
    Activations Density 0.000%

    No Known Activations