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. 27695
    Prev
    Next
    INDEX
    Explanations

    instances of confirmation and subjective opinion

    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
    0:0.02
    1:0.03
    2:0.15
    3:0.21
    4:0.09
    5:0.03
    6:0.07
    7:0.08
    8:0.03
    9:0.05
    10:0.08
    11:0.12
    Negative Logits
     WARN
    -1.36
    sic
    -1.32
    arus
    -1.28
    BUS
    -1.27
    crew
    -1.20
    fleet
    -1.19
    gi
    -1.18
    ゼウス
    -1.16
    gypt
    -1.11
    urst
    -1.11
    POSITIVE LOGITS
    olars
    1.32
     Carbuncle
    1.22
    aspberry
    1.18
    igham
    1.16
    iferation
    1.15
    ),"
    1.14
    natureconservancy
    1.14
    )'
    1.13
    %);
    1.09
    amins
    1.07
    Activations Density 0.028%

    No Known Activations