© 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. 40562
    Prev
    Next
    INDEX
    Explanations

    phrases indicating belief or opinion about a subject

    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
    0:0.04
    1:0.02
    2:0.22
    3:0.06
    4:0.13
    5:0.04
    6:0.06
    7:0.12
    8:0.09
    9:0.04
    10:0.05
    11:0.07
    Negative Logits
     bombshell
    -1.44
     cue
    -1.39
     operative
    -1.38
     upbeat
    -1.37
     indicator
    -1.35
     seismic
    -1.34
    "}],"
    -1.31
    ursday
    -1.31
    rounder
    -1.29
     ratified
    -1.26
    POSITIVE LOGITS
    ˈ
    1.70
    agna
    1.63
    selves
    1.56
    apego
    1.55
    \/\/
    1.54
    know
    1.52
    ngth
    1.50
    empt
    1.49
    foundland
    1.46
    esters
    1.44
    Activations Density 0.002%

    No Known Activations