© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 9333
    Prev
    Next
    INDEX
    Explanations

    phrases related to qualifications and metrics in assessments

    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
    0:0.04
    1:0.03
    2:0.33
    3:0.13
    4:0.08
    5:0.05
    6:0.03
    7:0.02
    8:0.05
    9:0.10
    10:0.05
    11:0.04
    Negative Logits
    interstitial
    -1.98
    iru
    -1.95
    yip
    -1.67
    tin
    -1.66
     Flavoring
    -1.59
    imei
    -1.58
    veyard
    -1.57
    Downloadha
    -1.53
    azard
    -1.49
     ];
    -1.49
    POSITIVE LOGITS
     meanwhile
    2.33
     however
    2.15
     beware
    1.75
     therefore
    1.56
    ource
    1.56
    beit
    1.55
     understandably
    1.54
     reprinted
    1.41
     doubtless
    1.39
     ain
    1.37
    Activations Density 0.702%

    No Known Activations