© 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 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. 25333
    Prev
    Next
    INDEX
    Explanations

    code elements and syntax related to programming constructs

    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
    508
    +0.14
    0.8%
    492
    +0.13
    0.7%
    367
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.14
    0.14
    130
    +0.13
    0.15
    33
    +0.12
    0.08
    Negative Logits
    ĻĤ
    -1.62
     pounds
    -1.54
     weight
    -1.53
     acres
    -1.50
     Hercules
    -1.49
    bones
    -1.45
    weight
    -1.45
     Weight
    -1.43
     mesh
    -1.39
     cane
    -1.36
    POSITIVE LOGITS
     discussions
    1.72
     analyses
    1.62
     analysis
    1.58
    ugin
    1.53
     publication
    1.51
    vision
    1.46
    rends
    1.46
    asks
    1.46
    ienne
    1.45
     defence
    1.44
    Activations Density 2.677%

    No Known Activations