© 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. 27869
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their appropriate usage within technical 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/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
    478
    +0.15
    0.8%
    382
    +0.13
    0.7%
    401
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.15
    0.07
    203
    +0.13
    0.05
    136
    +0.11
    -0.01
    Negative Logits
    ĻĤ
    -1.86
    ives
    -1.69
    ¾
    -1.65
    stown
    -1.63
     ads
    -1.54
    ory
    -1.50
    !),
    -1.48
     submissions
    -1.48
    ¹
    -1.47
     ðŁ
    -1.45
    POSITIVE LOGITS
    omitempty
    2.04
     preferably
    1.94
     namely
    1.90
     thereby
    1.84
     wherein
    1.83
    respectively
    1.78
     too
    1.76
    hereinafter
    1.76
     xcex
    1.76
    etc
    1.71
    Activations Density 0.383%

    No Known Activations