© 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. 44032
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions for access or participation, particularly in a context involving charges or eligibility

    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
    2:0.12
    3:0.14
    4:0.17
    5:0.02
    6:0.05
    7:0.13
    8:0.04
    9:0.04
    10:0.10
    11:0.08
    Negative Logits
    nikov
    -1.80
     outweigh
    -1.52
    ieved
    -1.51
    cknowled
    -1.50
     erosion
    -1.46
     tremend
    -1.45
    imity
    -1.44
     unison
    -1.40
    untled
    -1.39
     distingu
    -1.39
    POSITIVE LOGITS
     Salon
    1.45
     Comedy
    1.41
     Adult
    1.37
     Capitol
    1.36
     Desk
    1.34
    entle
    1.33
    Audio
    1.33
    interstitial
    1.31
     Theatre
    1.29
    DX
    1.28
    Activations Density 0.001%

    No Known Activations