© 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. 27639
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pure" and references to purity

    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
    156
    +0.21
    1.2%
    369
    +0.15
    0.9%
    47
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    448
    +0.21
    0.01
    198
    +0.15
    0.02
    326
    +0.13
    0.01
    Negative Logits
    han
    -1.60
    ···
    -1.49
    odot
    -1.41
    href
    -1.41
    ath
    -1.38
    clerosis
    -1.34
    atal
    -1.33
    abad
    -1.33
    innings
    -1.31
    pntd
    -1.31
    POSITIVE LOGITS
     enough
    2.44
    ¿½
    2.11
    bred
    2.11
    ī
    1.91
    Ģ
    1.90
    ↵↵
    1.89
    1.89
    1.89
    ↵↵
    1.89
    1.89
    Activations Density 0.133%

    No Known Activations