© 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. 0-MLP-SM
    11. 27050
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of substitution

    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
    376
    +0.14
    0.8%
    474
    +0.12
    0.7%
    449
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    449
    +0.14
    0.01
    0
    +0.12
    0.01
    325
    +0.11
    0.01
    Negative Logits
    ķ
    -4.11
    ĥ½
    -3.70
    ¸
    -3.63
    ¿
    -3.60
    »¿
    -3.58
    ³
    -3.56
    §
    -3.49
    ı
    -3.40
    »
    -3.34
    ²
    -3.33
    POSITIVE LOGITS
     chambers
    1.89
    cript
    1.79
    naire
    1.69
    istani
    1.68
    als
    1.65
    imal
    1.64
    ariate
    1.58
     example
    1.58
    ista
    1.56
    aria
    1.53
    Activations Density 0.007%

    No Known Activations