© 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. 26938
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and functions related to derivatives and transformations

    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
    359
    +0.15
    0.8%
    177
    +0.14
    0.8%
    164
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    359
    +0.15
    0.01
    181
    +0.14
    0.01
    177
    +0.11
    0.01
    Negative Logits
    ytes
    -1.60
     excellence
    -1.55
    APTER
    -1.45
     England
    -1.43
    opes
    -1.42
     superior
    -1.38
     quantification
    -1.38
    aling
    -1.37
     grounds
    -1.34
     logar
    -1.33
    POSITIVE LOGITS
    private
    1.59
     accord
    1.55
    {}{
    1.53
    procedure
    1.52
    quez
    1.50
    made
    1.47
    dup
    1.46
    jq
    1.45
    @{
    1.45
    volatile
    1.45
    Activations Density 0.009%

    No Known Activations