© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22014
    Prev
    Next
    INDEX
    Explanations

    elements related to video content and multimedia features

    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
    0:0.10
    1:0.04
    2:0.10
    3:0.07
    4:0.09
    5:0.06
    6:0.07
    7:0.04
    8:0.14
    9:0.14
    10:0.07
    11:0.03
    Negative Logits
    heit
    -1.68
    kefeller
    -1.59
    wu
    -1.36
    soType
    -1.35
    ylum
    -1.31
    ledged
    -1.27
    athered
    -1.25
    trust
    -1.23
    ModLoader
    -1.23
    sylv
    -1.22
    POSITIVE LOGITS
     clip
    1.28
     pops
    1.21
    ideos
    1.21
     buzz
    1.20
     drills
    1.19
     clips
    1.18
     embed
    1.18
     interrupt
    1.11
     VIDEOS
    1.11
     bang
    1.10
    Activations Density 0.009%

    No Known Activations