© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 11617
    Prev
    Next
    INDEX
    Explanations

    notions of comparison and evaluation in data analysis contexts

    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
    281
    +0.13
    0.8%
    395
    +0.11
    0.6%
    47
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.13
    0.05
    47
    +0.11
    0.05
    78
    +0.11
    -0.00
    Negative Logits
     hind
    -1.61
    organized
    -1.57
     Peng
    -1.55
     Laser
    -1.42
     abdom
    -1.38
    brid
    -1.37
    srep
    -1.37
     Jour
    -1.36
    apa
    -1.36
    ibal
    -1.35
    POSITIVE LOGITS
     value
    4.21
    value
    3.94
     Value
    3.74
     values
    3.56
    Value
    3.52
    values
    3.20
     Values
    3.18
    VALUE
    2.99
    Values
    2.81
    getValue
    2.69
    Activations Density 0.649%

    No Known Activations