© 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. 2-ATT-KK
    11. 23068
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and technical details within scientific and medical contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    quantifiable measurements and assessments in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.04
    2:0.15
    3:0.09
    4:0.05
    5:0.07
    6:0.02
    7:0.02
    8:0.25
    9:0.13
    10:0.05
    11:0.02
    Negative Logits
    aughed
    -1.36
    hement
    -1.32
    ener
    -1.30
    yles
    -1.29
    isi
    -1.27
    agna
    -1.26
    icion
    -1.26
    endi
    -1.25
    reon
    -1.24
    apist
    -1.24
    POSITIVE LOGITS
     differently
    1.41
     similarity
    1.36
     ceiling
    1.35
     diameter
    1.35
     overhead
    1.34
     difference
    1.33
     coefficient
    1.27
     裏�
    1.26
     precise
    1.23
     probabilities
    1.21
    Activations Density 0.030%

    No Known Activations