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. 5-ATT-KK
    6. 27337
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals and associated roles

    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
    0:0.21
    1:0.01
    2:0.12
    3:0.05
    4:0.09
    5:0.03
    6:0.04
    7:0.03
    8:0.19
    9:0.05
    10:0.07
    11:0.06
    Negative Logits
    グ
    -1.50
    norm
    -1.45
    gradient
    -1.40
     "$:/
    -1.39
    hered
    -1.38
    ˈ
    -1.37
    iform
    -1.35
    ="#
    -1.35
    course
    -1.33
    :(
    -1.33
    POSITIVE LOGITS
     respectively
    2.19
    isner
    1.50
    senal
    1.49
    és
    1.46
    enza
    1.44
    emale
    1.43
    rentice
    1.40
    eneg
    1.40
    enda
    1.38
    icz
    1.38
    Activations Density 0.138%

    No Known Activations