© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 37669
    Prev
    Next
    INDEX
    Explanations

    phrases indicating classifications or categories within 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
    1:0.01
    2:0.19
    3:0.13
    4:0.09
    5:0.04
    6:0.15
    7:0.06
    8:0.05
    9:0.06
    10:0.08
    11:0.06
    Negative Logits
     Polo
    -1.62
     Derby
    -1.54
     Catalyst
    -1.32
     Athletics
    -1.30
     Pace
    -1.29
     sponsorship
    -1.26
     Brid
    -1.25
     Bucks
    -1.23
     footh
    -1.23
     Hearts
    -1.23
    POSITIVE LOGITS
    "]=>
    1.72
    channelAvailability
    1.66
    agate
    1.53
    cult
    1.53
    machine
    1.50
    maxwell
    1.47
    dig
    1.44
    onyms
    1.42
    answer
    1.41
    perse
    1.40
    Activations Density 0.008%

    No Known Activations