© 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 · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 24822
    Prev
    Next
    INDEX
    Explanations

    references to al-Qaeda

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    2
    +0.19
    1.1%
    369
    +0.16
    0.9%
    450
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.19
    0.03
    450
    +0.16
    0.03
    372
    +0.13
    0.02
    Negative Logits
    ETHOD
    -1.57
    ONT
    -1.55
     laundering
    -1.55
     entire
    -1.52
    YPE
    -1.49
    auto
    -1.49
    alling
    -1.48
    idyl
    -1.46
    ableView
    -1.46
    CDATA
    -1.44
    POSITIVE LOGITS
    ·
    2.26
    Ĵ
    1.97
    º
    1.91
    ĥ½
    1.80
    ¾
    1.72
    «
    1.71
    leys
    1.71
    ppo
    1.70
    §
    1.70
    ¶
    1.70
    Activations Density 0.071%

    No Known Activations