© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 26150
    Prev
    Next
    INDEX
    Explanations

    dates, specifically the year 2013

    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
    312
    +0.15
    0.8%
    80
    +0.13
    0.7%
    463
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.15
    0.02
    316
    +0.13
    0.01
    7
    +0.12
    0.01
    Negative Logits
    oles
    -1.62
    tered
    -1.59
    ides
    -1.53
    lers
    -1.51
    akes
    -1.51
    Ĥ¬
    -1.50
    µ
    -1.47
     mustard
    -1.44
    ipp
    -1.38
    ropical
    -1.37
    POSITIVE LOGITS
    unnumbered
    2.00
     basis
    1.72
    brains
    1.50
    uppose
    1.42
     {@
    1.36
     member
    1.34
     finder
    1.34
     homework
    1.34
     ().
    1.34
     initialization
    1.30
    Activations Density 0.001%

    No Known Activations