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. 11318
    Prev
    Next
    INDEX
    Explanations

    specific player names and their associated positions or statistics

    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
    1:0.04
    2:0.10
    3:0.06
    4:0.07
    5:0.12
    6:0.12
    7:0.04
    8:0.09
    9:0.02
    10:0.03
    11:0.21
    Negative Logits
     squid
    -2.48
     Antar
    -2.25
    enium
    -2.19
     Madagascar
    -2.17
     secession
    -2.14
     recordings
    -2.13
     visas
    -2.09
     terminating
    -2.09
     differ
    -2.06
    gypt
    -2.05
    POSITIVE LOGITS
     RB
    4.39
     QB
    4.09
     WR
    4.00
     DB
    3.94
     FB
    3.91
     LW
    3.71
    RB
    3.69
     DL
    3.56
     OT
    3.54
     OL
    3.49
    Activations Density 0.011%

    No Known Activations