© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 32172
    Prev
    Next
    INDEX
    Explanations

    specific years and dates

    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
    34
    +0.14
    0.8%
    410
    +0.13
    0.7%
    342
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.14
    0.03
    364
    +0.13
    0.03
    145
    +0.12
    0.03
    Negative Logits
    ires
    -1.84
     respectively
    -1.75
    ()[
    -1.68
     longest
    -1.60
     last
    -1.52
     ages
    -1.47
    Inflater
    -1.45
     yes
    -1.39
    ire
    -1.39
    ~(
    -1.37
    POSITIVE LOGITS
     Gö
    1.48
     Party
    1.41
    chaft
    1.39
     Team
    1.37
     Ax
    1.35
    eLife
    1.35
     Kubernetes
    1.30
     Engineers
    1.30
    usiness
    1.29
    hui
    1.29
    Activations Density 0.043%

    No Known Activations