© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 27403
    Prev
    Next
    INDEX
    Explanations

    names of notable historical and public figures

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    156
    +0.32
    1.9%
    111
    +0.13
    0.7%
    434
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.32
    0.11
    156
    +0.13
    0.08
    271
    +0.10
    0.04
    Negative Logits
    ppat
    -1.53
    googleapis
    -1.33
    Ģ
    -1.31
     https
    -1.31
     Redistributions
    -1.30
    ubuntu
    -1.28
    ialog
    -1.27
     filtered
    -1.27
     unders
    -1.27
    MOESM
    -1.26
    POSITIVE LOGITS
    worth
    1.63
    ';
    1.62
    ?)
    1.54
    !--
    1.50
    ')
    1.49
    ously
    1.46
    ');
    1.41
    noreply
    1.40
    ?).
    1.39
     "'
    1.39
    Activations Density 0.313%

    No Known Activations