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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 202
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence structure elements

    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
    0:0.09
    1:0.02
    2:0.09
    3:0.03
    4:0.05
    5:0.03
    6:0.22
    7:0.05
    8:0.12
    9:0.21
    10:0.02
    11:0.02
    Negative Logits
     sty
    -3.78
     Sok
    -3.62
     Sting
    -3.62
     webs
    -3.53
     silk
    -3.45
    aleigh
    -3.42
    foundland
    -3.41
     Knot
    -3.41
     puff
    -3.37
     Brist
    -3.36
    POSITIVE LOGITS
     Ramirez
    12.24
    Ram
    7.60
     Ramos
    6.57
    irez
    6.05
     Ram
    5.72
     Moreno
    5.38
     Rodriguez
    5.16
    rez
    4.89
     Perez
    4.86
     Ramsey
    4.76
    Activations Density 0.001%

    No Known Activations