© 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. 22900
    Prev
    Next
    INDEX
    Explanations

    mentions of specific companies, organizations, or government officials as subjects of discussions or actions

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

    references to companies and their involvement in societal issues

    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
    0:0.03
    1:0.02
    2:0.27
    3:0.04
    4:0.04
    5:0.12
    6:0.02
    7:0.03
    8:0.06
    9:0.23
    10:0.06
    11:0.03
    Negative Logits
    croft
    -1.28
     haunt
    -1.20
     stalk
    -1.17
     spa
    -1.15
     hatch
    -1.13
     brun
    -1.13
    ‐
    -1.12
     hus
    -1.11
     humili
    -1.10
     spoiler
    -1.10
    POSITIVE LOGITS
    ItemTracker
    1.34
     Cosponsors
    1.33
    atown
    1.29
     manufactures
    1.27
     tradem
    1.25
    ngth
    1.22
    areth
    1.20
    jac
    1.18
     Industry
    1.18
    swick
    1.18
    Activations Density 0.089%

    No Known Activations