© 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. 2-MLP-SM
    11. 27103
    Prev
    Next
    INDEX
    Explanations

    references to external contexts or environments

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    123
    +0.14
    0.8%
    448
    +0.14
    0.8%
    316
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    448
    +0.14
    0.03
    339
    +0.14
    0.05
    173
    +0.10
    0.02
    Negative Logits
    »¿
    -1.83
    NdEx
    -1.78
    ĨĴ
    -1.70
     dubbed
    -1.69
    ©
    -1.68
    Ļª
    -1.63
    ı
    -1.57
    ĵ
    -1.55
    Ĥ¬
    -1.55
    Ŀ
    -1.55
    POSITIVE LOGITS
     Areas
    1.81
     Factors
    1.76
     thoughts
    1.66
     part
    1.55
     factors
    1.55
     Balance
    1.54
     _________________________________
    1.51
    amins
    1.49
     Comments
    1.48
     Facts
    1.47
    Activations Density 0.871%

    No Known Activations