© 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. 22797
    Prev
    Next
    INDEX
    Explanations

    concepts related to status or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to locations or physical attributes

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    1:0.04
    2:0.11
    3:0.08
    4:0.14
    5:0.09
    6:0.04
    7:0.03
    8:0.14
    9:0.13
    10:0.05
    11:0.04
    Negative Logits
    igham
    -1.43
    fen
    -1.31
    uart
    -1.28
    atography
    -1.27
    instead
    -1.24
    paces
    -1.23
     Maul
    -1.21
    ourning
    -1.20
    BUS
    -1.20
    mt
    -1.19
    POSITIVE LOGITS
    iable
    1.33
     quot
    1.23
     Factor
    1.18
    ailable
    1.17
     lies
    1.16
     aspir
    1.14
    angled
    1.14
     appetite
    1.11
     afloat
    1.09
    nered
    1.09
    Activations Density 0.001%

    No Known Activations