© 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. 1154
    Prev
    Next
    INDEX
    Explanations

    verbs and actions indicative of changes or effects in various contexts

    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
    0:0.13
    1:0.14
    2:0.05
    3:0.03
    4:0.04
    5:0.27
    6:0.03
    7:0.02
    8:0.11
    9:0.04
    10:0.04
    11:0.04
    Negative Logits
     purchased
    -1.52
     Proc
    -1.38
    ettlement
    -1.36
    anto
    -1.35
    kat
    -1.32
    cill
    -1.32
    endi
    -1.30
    eez
    -1.30
     signings
    -1.29
     Cerberus
    -1.29
    POSITIVE LOGITS
    eatures
    2.00
    theless
    1.65
    retty
    1.59
    etheless
    1.56
     behavi
    1.52
    interstitial
    1.50
     slic
    1.46
    ensibly
    1.45
    anwhile
    1.45
     Sloven
    1.43
    Activations Density 0.086%

    No Known Activations