© 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. MLP Post
    9. 0-MLP-SM
    11. 30316
    Prev
    Next
    INDEX
    Explanations

    entries with a consistent structure or format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    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
    210
    +0.17
    0.9%
    59
    +0.12
    0.6%
    307
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.17
    0.05
    495
    +0.12
    0.05
    499
    +0.11
    0.05
    Negative Logits
    ĻĤ
    -1.82
    enne
    -1.63
    £
    -1.61
    ¥
    -1.61
    git
    -1.57
    ournal
    -1.51
    encer
    -1.51
    elin
    -1.51
    ĸ
    -1.50
    ledge
    -1.46
    POSITIVE LOGITS
     warranty
    1.58
     stall
    1.52
    pot
    1.37
    hores
    1.37
     vectors
    1.34
    hips
    1.34
     prominently
    1.33
    resses
    1.32
     advertised
    1.29
     couples
    1.29
    Activations Density 0.073%

    No Known Activations