© 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. 4-RES-SM
    11. 9856
    Prev
    Next
    INDEX
    Explanations

    specific structured data formats or syntax indicative of web content

    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
    21
    +0.17
    0.9%
    271
    +0.16
    0.9%
    258
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.17
    0.02
    473
    +0.16
    0.02
    107
    +0.14
    0.00
    Negative Logits
    adier
    -1.91
    inates
    -1.66
    apine
    -1.64
     mine
    -1.57
    apolis
    -1.53
     accounts
    -1.49
     kills
    -1.43
    ych
    -1.43
     Barr
    -1.42
     QC
    -1.41
    POSITIVE LOGITS
    ¶
    1.83
    ŀ
    1.82
    ¬
    1.81
    Ĥ
    1.81
    ±
    1.79
    Ĩ
    1.79
    xhtml
    1.77
    DTD
    1.76
    ©
    1.75
    dtd
    1.70
    Activations Density 0.094%

    No Known Activations