© 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. 2-RES-SM
    11. 27704
    Prev
    Next
    INDEX
    Explanations

    elements related to policy and procedural instructions

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    407
    +0.15
    0.8%
    317
    +0.13
    0.7%
    353
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.15
    0.16
    317
    +0.13
    0.17
    118
    +0.13
    0.22
    Negative Logits
    Īĺ
    -2.47
    Ļª
    -2.03
    ¿½
    -1.72
    ĻĤ
    -1.71
    ģ
    -1.68
    ľ
    -1.65
    »¿
    -1.60
    £
    -1.53
    «
    -1.47
    ·¸
    -1.46
    POSITIVE LOGITS
    wordpress
    1.56
    ”
    1.49
    qa
    1.43
     my
    1.39
     =>
    1.37
     lately
    1.34
    ãĢİ
    1.30
    ','
    1.27
     today
    1.26
    ”,
    1.26
    Activations Density 7.996%

    No Known Activations