© 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. 10763
    Prev
    Next
    INDEX
    Explanations

    different variations and forms of the word "stripe."

    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
    +0.31
    1.8%
    232
    +0.13
    0.7%
    202
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.31
    0.03
    386
    +0.13
    0.02
    351
    +0.10
    0.04
    Negative Logits
     hosts
    -1.66
    iast
    -1.50
    nas
    -1.46
     host
    -1.45
     done
    -1.43
     spirits
    -1.38
    nos
    -1.34
     toll
    -1.30
     reliance
    -1.30
     Ministry
    -1.30
    POSITIVE LOGITS
    Ĭ
    4.27
    ı
    3.55
    ĩ
    3.53
    Ī
    3.48
    ¼
    3.47
    ģ
    3.46
    Ħ
    3.45
    Į
    3.44
    Ŀ
    3.44
    IJ
    3.43
    Activations Density 0.348%

    No Known Activations