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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 21382
    Prev
    Next
    INDEX
    Explanations

    phrases related to customization and adaptability

    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
    0:0.04
    1:0.02
    2:0.05
    3:0.21
    4:0.03
    5:0.08
    6:0.01
    7:0.06
    8:0.03
    9:0.01
    10:0.36
    11:0.04
    Negative Logits
    tein
    -1.91
    >)
    -1.87
     aborted
    -1.83
    esides
    -1.82
     Promise
    -1.82
    Charges
    -1.80
     laure
    -1.77
     Ending
    -1.76
     apologizing
    -1.76
    ileaks
    -1.72
    POSITIVE LOGITS
     needs
    2.63
     circumstances
    2.61
     workload
    2.53
     conditions
    2.49
     environments
    2.36
     demands
    2.31
     occasion
    2.30
     pressures
    2.24
     situations
    2.23
     stimuli
    2.23
    Activations Density 0.411%

    No Known Activations