© 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. 24608
    Prev
    Next
    INDEX
    Explanations

    specific programming language syntax or structure

    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
    111
    +0.77
    18.2%
    156
    +0.62
    14.7%
    71
    +0.05
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.77
    0.98
    71
    +0.62
    0.97
    156
    +0.05
    0.96
    Negative Logits
    ħ
    -2.64
    ľĵ
    -2.61
    Ľ
    -2.59
    ¿½
    -2.58
    ®
    -2.57
    ij
    -2.51
    ĥ½
    -2.51
    ¿
    -2.51
    ½
    -2.50
    ¦
    -2.47
    POSITIVE LOGITS
     polÃŃ
    0.94
     fundament
    0.91
     aboard
    0.91
    iang
    0.88
     concentration
    0.88
     hype
    0.87
     inheritance
    0.86
     invalid
    0.85
    istor
    0.83
    orph
    0.83
    Activations Density 2.209%

    No Known Activations