© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22729
    Prev
    Next
    INDEX
    Explanations

    names of people or entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    proper nouns, specifically names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.13
    1:0.02
    2:0.13
    3:0.07
    4:0.02
    5:0.09
    6:0.02
    7:0.08
    8:0.03
    9:0.11
    10:0.16
    11:0.09
    Negative Logits
    theless
    -1.70
    etheless
    -1.63
     millenn
    -1.26
    ccording
    -1.16
     incumb
    -1.14
     polarization
    -1.13
     horizont
    -1.11
    BuyableInstoreAndOnline
    -1.10
     conformity
    -1.09
     unbeliev
    -1.07
    POSITIVE LOGITS
    icz
    1.44
    quez
    1.39
    herty
    1.37
    owicz
    1.27
    enberg
    1.25
     QC
    1.25
    ham
    1.24
    ben
    1.20
    wine
    1.18
    owski
    1.17
    Activations Density 0.580%

    No Known Activations