© 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 · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 13290
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and symbols

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.19
    1.1%
    397
    +0.14
    0.8%
    271
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    506
    +0.19
    0.01
    178
    +0.14
    0.01
    421
    +0.14
    0.01
    Negative Logits
    atics
    -2.02
    iginally
    -1.71
    ions
    -1.61
    aries
    -1.57
    ennial
    -1.55
    ually
    -1.52
    baum
    -1.45
    rait
    -1.45
     successfully
    -1.44
    onymous
    -1.43
    POSITIVE LOGITS
    IJ
    5.17
    ĥ
    4.89
    ĵ
    4.83
    Īĺ
    4.72
    ©
    4.71
    ĨĴ
    4.64
    Ķ
    4.62
    ī
    4.62
    Ĭ
    4.58
    ĻĤ
    4.57
    Activations Density 0.017%

    No Known Activations