© 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. 26946
    Prev
    Next
    INDEX
    Explanations

    mentions of significant numerical values or statistics

    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
    88
    +0.14
    0.8%
    400
    +0.12
    0.7%
    65
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.14
    0.11
    209
    +0.12
    0.09
    495
    +0.12
    0.07
    Negative Logits
    ples
    -1.54
    pec
    -1.54
    aurus
    -1.41
     yourselves
    -1.39
     yourself
    -1.39
     supplements
    -1.38
     shocks
    -1.35
     enough
    -1.34
    ations
    -1.34
    tal
    -1.33
    POSITIVE LOGITS
    ¶
    1.75
    burg
    1.55
    :`
    1.52
    Ł
    1.48
     correspondent
    1.41
     .$$
    1.40
    Ĺ
    1.35
    unreadable
    1.35
    ³
    1.33
    coded
    1.29
    Activations Density 0.108%

    No Known Activations