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. 5-ATT-KK
    6. 19258
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "Don’t."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.07
    2:0.08
    3:0.08
    4:0.08
    5:0.07
    6:0.09
    7:0.11
    8:0.08
    9:0.08
    10:0.07
    11:0.07
    Negative Logits
     behavi
    -2.29
     behav
    -1.70
    ��
    -1.61
     looph
    -1.57
     Wag
    -1.51
    Reviewer
    -1.51
    ]]
    -1.49
    "}
    -1.48
    antics
    -1.47
    merce
    -1.47
    POSITIVE LOGITS
     liner
    1.60
     QC
    1.54
    TION
    1.52
    ula
    1.42
    iles
    1.41
     /
    1.37
    Products
    1.36
    apan
    1.35
    itars
    1.30
    urances
    1.29
    Activations Density 0.000%

    No Known Activations