Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3110
    Prev
    Next
    INDEX
    Explanations

    specific phrases or sentence structures

    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
    0:0.04
    1:0.06
    2:0.03
    3:0.04
    4:0.03
    5:0.03
    6:0.13
    7:0.02
    8:0.04
    9:0.48
    10:0.02
    11:0.03
    Negative Logits
     Kab
    -3.95
    amps
    -3.80
     chalk
    -3.64
    Snap
    -3.46
     Mub
    -3.43
    uba
    -3.38
    amb
    -3.31
     Kung
    -3.27
     saliva
    -3.27
     Sabb
    -3.16
    POSITIVE LOGITS
    OR
    6.12
    ORS
    5.21
    orio
    5.17
     Lor
    5.08
    ori
    5.02
    oris
    4.97
    oros
    4.93
    vor
    4.90
     Bor
    4.82
    or
    4.81
    Activations Density 0.050%

    No Known Activations