© 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. 9-ATT-KK
    11. 15983
    Prev
    Next
    INDEX
    Explanations

    phrases related to community infrastructure and development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.04
    2:0.10
    3:0.18
    4:0.06
    5:0.11
    6:0.03
    7:0.13
    8:0.07
    9:0.03
    10:0.07
    11:0.04
    Negative Logits
    ネ
    -2.76
    ERROR
    -2.61
    ッド
    -2.58
    Synopsis
    -2.49
    ゴン
    -2.49
     angrily
    -2.46
    GOP
    -2.44
    >]
    -2.40
    �
    -2.32
    �
    -2.32
    POSITIVE LOGITS
     licences
    3.36
     pubs
    2.91
     programmes
    2.76
     flavours
    2.74
     licence
    2.71
     neighbourhoods
    2.63
     supermarkets
    2.63
     cafes
    2.60
     redevelop
    2.60
     ageing
    2.56
    Activations Density 0.415%

    No Known Activations