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

    Neuronpedia

    APICircuit 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. 20709
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding serious societal issues and challenges

    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
    0:0.02
    1:0.03
    2:0.02
    3:0.12
    4:0.04
    5:0.10
    6:0.03
    7:0.10
    8:0.04
    9:0.01
    10:0.17
    11:0.26
    Negative Logits
    >)
    -3.41
    )</
    -2.98
    >]
    -2.88
    >>>>
    -2.85
    =#
    -2.83
    [/
    -2.69
    =]
    -2.67
    ]:
    -2.65
    ]=
    -2.63
    ][/
    -2.62
    POSITIVE LOGITS
    .
    2.66
     amid
    2.43
     according
    2.16
     fuelled
    2.10
     thanks
    2.07
     ahead
    2.06
     while
    2.04
     because
    1.96
     despite
    1.95
     based
    1.90
    Activations Density 1.076%

    No Known Activations