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. 7683
    Prev
    Next
    INDEX
    Explanations

    phrases that reference specific historical or significant events

    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
    0:0.01
    1:0.02
    2:0.04
    3:0.32
    4:0.01
    5:0.02
    6:0.07
    7:0.08
    8:0.06
    9:0.04
    10:0.08
    11:0.19
    Negative Logits
    andy
    -1.39
    ��
    -1.29
     folders
    -1.21
    tumblr
    -1.21
     dearly
    -1.20
    gnu
    -1.18
    ugg
    -1.17
    ooth
    -1.17
    enance
    -1.15
    recated
    -1.14
    POSITIVE LOGITS
    enium
    1.54
    akedown
    1.40
     journey
    1.34
     Sequence
    1.34
     sequence
    1.22
     ascent
    1.20
     leap
    1.17
     descent
    1.17
     hostilities
    1.17
     sentence
    1.15
    Activations Density 0.014%

    No Known Activations