© 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. MLP Post
    9. 0-MLP-SM
    11. 27137
    Prev
    Next
    INDEX
    Explanations

    standardized coding structures or configurations

    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
    19
    +0.13
    0.7%
    469
    +0.13
    0.7%
    291
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.13
    0.40
    53
    +0.13
    0.42
    56
    +0.13
    0.11
    Negative Logits
    ently
    -1.77
    ults
    -1.74
    arily
    -1.74
    ientos
    -1.71
    utes
    -1.68
    utely
    -1.65
    uppose
    -1.60
    ients
    -1.58
    paring
    -1.52
    ĻĤ
    -1.47
    POSITIVE LOGITS
     extent
    1.69
     generality
    1.51
     possibility
    1.50
     balance
    1.46
     balloon
    1.44
     voice
    1.38
     fraction
    1.36
     burden
    1.29
     puck
    1.28
     annotation
    1.28
    Activations Density 4.648%

    No Known Activations