© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 7845
    Prev
    Next
    INDEX
    Explanations

    questions and concerns about credibility and evidence in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.07
    2:0.08
    3:0.09
    4:0.10
    5:0.12
    6:0.07
    7:0.07
    8:0.07
    9:0.11
    10:0.05
    11:0.09
    Negative Logits
     Bulgar
    -2.75
    �
    -2.72
     Romanian
    -2.63
    \\
    -2.43
    APH
    -2.40
    ,,,,
    -2.36
    agne
    -2.32
    French
    -2.29
     French
    -2.23
    ihad
    -2.20
    POSITIVE LOGITS
    )?
    4.45
    ?),
    3.44
    ?).
    3.40
    ?)
    3.24
    ?
    3.11
    ?)
    2.88
    oken
    2.83
    )).
    2.79
    answered
    2.73
    ?:
    2.67
    Activations Density 0.001%

    No Known Activations