© 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. 2-ATT-KK
    6. 22510
    Prev
    Next
    INDEX
    Explanations

    information about events, incidents, or stories that have gained attention in the media

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases that reference actions related to "picking up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.02
    2:0.20
    3:0.06
    4:0.14
    5:0.03
    6:0.02
    7:0.02
    8:0.28
    9:0.08
    10:0.04
    11:0.02
    Negative Logits
    rency
    -1.50
    oking
    -1.47
    resso
    -1.45
    forestation
    -1.42
    idia
    -1.41
    govtrack
    -1.40
    pired
    -1.39
    ogun
    -1.37
    parable
    -1.37
    oir
    -1.34
    POSITIVE LOGITS
    cale
    1.30
     DHCP
    1.29
     Rez
    1.25
     ransom
    1.22
     Viktor
    1.22
     axe
    1.21
     裏�
    1.20
     KEY
    1.20
     Zup
    1.20
    �
    1.18
    Activations Density 0.008%

    No Known Activations