© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26946
    Prev
    Next
    INDEX
    Explanations

    terms referring to comparisons or classifications of methods, conditions, or substances

    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
    17
    +0.14
    0.8%
    404
    +0.13
    0.8%
    255
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    108
    +0.14
    0.09
    404
    +0.13
    0.08
    179
    +0.12
    0.08
    Negative Logits
     expressed
    -1.77
    ided
    -1.72
     grandson
    -1.60
    eous
    -1.56
    ffected
    -1.54
     infants
    -1.54
    ]{.
    -1.50
     pronounced
    -1.48
     propagated
    -1.47
    wered
    -1.45
    POSITIVE LOGITS
    . 
    1.94
    starter
    1.78
    ĭ
    1.78
    :`
    1.66
    ľĵ
    1.62
    ĥ½
    1.62
    forge
    1.61
    ®
    1.59
    §
    1.59
     mailing
    1.58
    Activations Density 0.915%

    No Known Activations