© 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. 27080
    Prev
    Next
    INDEX
    Explanations

    licensing information related to software distribution

    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
    225
    +0.15
    0.8%
    368
    +0.13
    0.7%
    49
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.15
    0.02
    225
    +0.13
    0.03
    330
    +0.12
    0.03
    Negative Logits
     interest
    -1.82
     millions
    -1.64
     thereafter
    -1.52
    ende
    -1.49
     tens
    -1.48
     magn
    -1.46
     opportunities
    -1.46
     efforts
    -1.44
     tenants
    -1.42
     attracted
    -1.41
    POSITIVE LOGITS
    Category
    1.51
    ested
    1.48
    iani
    1.48
    ilst
    1.46
    TestCase
    1.44
    ibi
    1.42
    MRI
    1.42
    oned
    1.41
    vist
    1.39
    udson
    1.36
    Activations Density 0.067%

    No Known Activations