© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22741
    Prev
    Next
    INDEX
    Explanations

    technical information and details in a document

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

    technical references and regulations related to network and internet services

    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
    0:0.06
    1:0.02
    2:0.14
    3:0.08
    4:0.21
    5:0.08
    6:0.04
    7:0.02
    8:0.04
    9:0.14
    10:0.08
    11:0.02
    Negative Logits
    netflix
    -1.47
    uscript
    -1.33
    gor
    -1.30
    rely
    -1.29
     clutch
    -1.27
    isite
    -1.27
     dot
    -1.27
    imar
    -1.22
    @
    -1.22
     trump
    -1.20
    POSITIVE LOGITS
    Definition
    1.63
     Directors
    1.60
     Execution
    1.59
    Mine
    1.45
    Creat
    1.43
    Corp
    1.42
     Madness
    1.41
     guiActiveUnfocused
    1.40
    inctions
    1.39
    士
    1.34
    Activations Density 0.031%

    No Known Activations