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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10502
    Prev
    Next
    INDEX
    Explanations

    elements related to profiles or identification in various contexts

    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
    0:0.02
    1:0.02
    2:0.05
    3:0.16
    4:0.02
    5:0.07
    6:0.06
    7:0.28
    8:0.07
    9:0.05
    10:0.06
    11:0.09
    Negative Logits
    atti
    -1.38
     repe
    -1.33
    stead
    -1.33
     braking
    -1.29
     extingu
    -1.26
     stranded
    -1.18
    �
    -1.17
     abandon
    -1.16
    asio
    -1.16
    amaz
    -1.16
    POSITIVE LOGITS
     Preferences
    1.51
     Occupations
    1.49
     Parables
    1.44
     Newsp
    1.36
     Newspaper
    1.31
     Profession
    1.23
    umbnails
    1.22
    OTOS
    1.19
     Onion
    1.19
    Names
    1.19
    Activations Density 0.010%

    No Known Activations