© 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. 2-RES-SM
    11. 10764
    Prev
    Next
    INDEX
    Explanations

    references to average or median values

    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
    11
    +0.13
    0.8%
    457
    +0.13
    0.7%
    112
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    112
    +0.13
    0.02
    457
    +0.13
    0.02
    485
    +0.12
    0.02
    Negative Logits
    uez
    -1.61
    cert
    -1.59
    uet
    -1.59
     inducible
    -1.52
    asser
    -1.50
     critically
    -1.47
     BGCOLOR
    -1.44
     remanded
    -1.43
    sufficient
    -1.42
    compatible
    -1.40
    POSITIVE LOGITS
     ages
    1.89
     well
    1.71
     appearances
    1.68
     values
    1.64
    cale
    1.64
     liking
    1.61
    boro
    1.61
     daily
    1.57
    erton
    1.54
     viewer
    1.51
    Activations Density 0.115%

    No Known Activations