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. 9-ATT-KK
    6. 11228
    Prev
    Next
    INDEX
    Explanations

    occurrences of significant events or situations that involve problems or challenges

    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
    3:0.10
    4:0.03
    5:0.05
    6:0.02
    7:0.03
    8:0.02
    9:0.02
    10:0.56
    11:0.02
    Negative Logits
     periodically
    -3.32
     weekly
    -2.90
     occasionally
    -2.68
     occasional
    -2.53
     intermitt
    -2.51
     regularly
    -2.48
     monthly
    -2.48
     quarterly
    -2.47
     frequently
    -2.46
     hourly
    -2.41
    POSITIVE LOGITS
    cedented
    2.51
    ankind
    2.24
    ��
    2.21
    heid
    2.20
    azes
    2.12
    ceivable
    2.12
    thood
    2.09
    sight
    2.08
    sein
    2.08
    cig
    2.08
    Activations Density 0.152%

    No Known Activations