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. 18780
    Prev
    Next
    INDEX
    Explanations

    references to failure or decline

    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
    1:0.08
    2:0.09
    3:0.08
    4:0.08
    5:0.07
    6:0.09
    7:0.08
    8:0.07
    9:0.09
    10:0.07
    11:0.07
    Negative Logits
     NV
    -2.87
     anticip
    -2.75
    uve
    -2.58
    icip
    -2.57
     puppy
    -2.52
    leon
    -2.46
     LX
    -2.45
     Jaguar
    -2.43
     indo
    -2.41
     LG
    -2.40
    POSITIVE LOGITS
    Merit
    3.82
    alcohol
    2.92
     Alcohol
    2.91
     Halls
    2.83
    burse
    2.79
    Amount
    2.69
    Cas
    2.69
     Burns
    2.66
     Gilmore
    2.65
     Gamble
    2.63
    Activations Density 0.000%

    No Known Activations