© 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. 24735
    Prev
    Next
    INDEX
    Explanations

    specific syntactical patterns and assignments in programming languages

    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
    98
    +0.12
    0.7%
    416
    +0.12
    0.6%
    363
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    363
    +0.12
    0.07
    230
    +0.12
    -0.02
    50
    +0.11
    0.02
    Negative Logits
     favour
    -1.61
    ô
    -1.58
     British
    -1.54
     arriv
    -1.40
    iff
    -1.35
     £
    -1.33
    ;</
    -1.32
    ermal
    -1.31
    dern
    -1.31
    atorium
    -1.28
    POSITIVE LOGITS
    º
    3.91
    Ķ
    3.73
    Īĺ
    3.71
    ·¸
    3.70
    ĻĤ
    3.70
    Ľ
    3.66
    Ħ
    3.65
    ¬
    3.63
                ↵
    3.59
    ↵↵
    3.59
    Activations Density 2.256%

    No Known Activations