© 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. 2-ATT-KK
    11. 22635
    Prev
    Next
    INDEX
    Explanations

    technical details about electronics and product features

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

    instances of past actions or events in an article

    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
    0:0.12
    1:0.02
    2:0.10
    3:0.18
    4:0.15
    5:0.08
    6:0.06
    7:0.02
    8:0.07
    9:0.06
    10:0.06
    11:0.02
    Negative Logits
     pione
    -1.18
    ディ
    -1.18
    イト
    -1.18
    etheless
    -1.13
     behavi
    -1.08
    ngth
    -1.05
     teasp
    -1.04
     apt
    -0.96
    utch
    -0.96
    stellar
    -0.96
    POSITIVE LOGITS
    imester
    1.46
     introdu
    1.34
    sale
    1.34
     arrives
    1.21
    ropolis
    1.14
    iversary
    1.12
    ashes
    1.10
    azeera
    1.09
    pection
    1.07
    hal
    1.07
    Activations Density 0.021%

    No Known Activations