© 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. 27931
    Prev
    Next
    INDEX
    Explanations

    instances of the letter "E" in various contexts

    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
    9
    +0.11
    0.6%
    325
    +0.11
    0.6%
    116
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.11
    0.07
    25
    +0.11
    0.05
    377
    +0.10
    0.05
    Negative Logits
     grown
    -1.55
     occasion
    -1.54
     thereof
    -1.41
     Trudeau
    -1.41
     thousands
    -1.34
     millions
    -1.34
     passing
    -1.33
     ways
    -1.32
     anymore
    -1.32
     dead
    -1.31
    POSITIVE LOGITS
    £
    1.71
    Īĺ
    1.65
    ishes
    1.60
    ½
    1.58
    estinal
    1.56
    vet
    1.56
    İ
    1.54
    hall
    1.53
    heim
    1.53
    stein
    1.53
    Activations Density 0.027%

    No Known Activations