© 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. 9-ATT-KK
    6. 11536
    Prev
    Next
    INDEX
    Explanations

    terms related to hostage situations and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.06
    3:0.20
    4:0.04
    5:0.07
    6:0.01
    7:0.06
    8:0.03
    9:0.02
    10:0.36
    11:0.02
    Negative Logits
    requires
    -2.50
     yearly
    -2.49
     perenn
    -2.40
     heirs
    -2.30
     annually
    -2.19
     perpetually
    -2.19
    conservancy
    -2.03
     fertile
    -1.93
    always
    -1.91
     aspire
    -1.90
    POSITIVE LOGITS
     announcement
    2.19
     yesterday
    2.17
    Tuesday
    2.15
     outburst
    2.13
     Tuesday
    2.12
     findings
    2.06
     outage
    2.04
     Disapp
    2.03
     incident
    2.02
     tweeted
    2.01
    Activations Density 0.385%

    No Known Activations