© 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. 14069
    Prev
    Next
    INDEX
    Explanations

    references to census data and related statistics

    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
    35
    +0.16
    1.0%
    397
    +0.14
    0.8%
    378
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    368
    +0.16
    0.01
    501
    +0.14
    0.01
    378
    +0.13
    0.01
    Negative Logits
    MIT
    -1.63
    atitis
    -1.61
    FPar
    -1.50
    unnumbered
    -1.46
    atern
    -1.42
     physic
    -1.37
    hydration
    -1.37
    ospor
    -1.36
    coming
    -1.34
    olip
    -1.34
    POSITIVE LOGITS
     clip
    1.88
    est
    1.67
     turnout
    1.64
     cutoff
    1.55
     estimate
    1.50
     realization
    1.49
     crest
    1.44
     coordinates
    1.43
     classification
    1.42
     report
    1.42
    Activations Density 0.055%

    No Known Activations