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

    Neuronpedia

    Jacobian LensNEW
    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. 943
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific actions or situations that may lead to feelings of discomfort or injury

    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
    0:0.09
    1:0.02
    2:0.13
    3:0.26
    4:0.06
    5:0.07
    6:0.03
    7:0.10
    8:0.05
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
    Education
    -2.91
     Education
    -2.90
    Educ
    -2.82
     Religious
    -2.74
    Public
    -2.73
     Political
    -2.68
     Organizations
    -2.67
     Communities
    -2.65
     Families
    -2.63
    Government
    -2.63
    POSITIVE LOGITS
     bends
    3.89
     piston
    3.78
     torque
    3.65
     knots
    3.57
     plun
    3.52
     airflow
    3.44
     coil
    3.40
     rope
    3.37
     groove
    3.36
     perpendicular
    3.36
    Activations Density 0.884%

    No Known Activations