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. 3-ATT-KK
    6. 8642
    Prev
    Next
    INDEX
    Explanations

    the word "always" and its variations, indicating a focus on consistency and continuity in actions or traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.03
    2:0.13
    3:0.12
    4:0.02
    5:0.04
    6:0.06
    7:0.05
    8:0.08
    9:0.07
    10:0.13
    11:0.18
    Negative Logits
    lying
    -1.29
    witch
    -1.19
    ��
    -1.09
    heimer
    -1.07
    mort
    -1.00
    catentry
    -0.96
     undisclosed
    -0.96
     inactive
    -0.96
    Mask
    -0.95
     unspecified
    -0.93
    POSITIVE LOGITS
     Perspective
    1.14
    ィ
    1.12
    vae
    1.09
    izens
    1.04
     thri
    1.03
    ounters
    1.03
    oglobin
    1.03
     echoes
    1.02
     fascinated
    1.02
    akable
    1.01
    Activations Density 0.007%

    No Known Activations