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. 9-ATT-KK
    6. 18733
    Prev
    Next
    INDEX
    Explanations

    references to specific dates, particularly holidays

    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
    0:0.07
    1:0.08
    2:0.08
    3:0.08
    4:0.06
    5:0.07
    6:0.08
    7:0.08
    8:0.09
    9:0.08
    10:0.08
    11:0.09
    Negative Logits
    thood
    -3.61
    venant
    -2.88
    plete
    -2.84
    stellar
    -2.81
    phans
    -2.78
    INESS
    -2.76
    ributed
    -2.68
    ouble
    -2.65
    acter
    -2.65
    lif
    -2.64
    POSITIVE LOGITS
     Ukip
    3.63
     Indra
    3.43
     Farage
    3.27
     Canary
    3.10
     Esk
    3.08
     Cherokee
    2.93
     UKIP
    2.92
     Pi
    2.90
     Chow
    2.85
     Sirius
    2.84
    Activations Density 0.000%

    No Known Activations