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. 2711
    Prev
    Next
    INDEX
    Explanations

    names of individuals and teams associated with cycling

    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
    0:0.04
    1:0.03
    2:0.06
    3:0.06
    4:0.06
    5:0.04
    6:0.27
    7:0.08
    8:0.05
    9:0.07
    10:0.12
    11:0.07
    Negative Logits
    worms
    -1.47
     gesture
    -1.45
    SPONSORED
    -1.44
    yang
    -1.42
     Dictionary
    -1.42
     grammar
    -1.40
    anchester
    -1.38
     Speech
    -1.35
     posture
    -1.35
    ary
    -1.33
    POSITIVE LOGITS
    ワン
    2.01
    veyard
    1.82
    ��
    1.67
    opers
    1.63
     sidx
    1.62
    ffen
    1.59
     sqor
    1.56
    BuyableInstoreAndOnline
    1.52
    nil
    1.51
    antam
    1.51
    Activations Density 0.001%

    No Known Activations