© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 11674
    Prev
    Next
    INDEX
    Explanations

    specific product names and model identifiers

    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
    21
    +0.27
    1.6%
    385
    +0.12
    0.7%
    255
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.27
    0.11
    397
    +0.12
    0.10
    78
    +0.10
    0.00
    Negative Logits
    Govern
    -1.39
     Perth
    -1.35
     Gaz
    -1.34
     Tas
    -1.33
    eless
    -1.33
    tem
    -1.32
    rained
    -1.31
    tm
    -1.30
    etr
    -1.29
     refres
    -1.27
    POSITIVE LOGITS
     Reds
    1.73
    rike
    1.71
    III
    1.70
     Franco
    1.69
    ström
    1.65
     strike
    1.64
    inson
    1.53
    jä
    1.51
     III
    1.50
    aphragm
    1.48
    Activations Density 1.893%

    No Known Activations