© 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. 2-MLP-SM
    11. 25810
    Prev
    Next
    INDEX
    Explanations

    references to historical events and figures related to architecture and beauty standards

    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
    156
    +0.20
    1.1%
    455
    +0.15
    0.9%
    79
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    42
    +0.20
    0.16
    251
    +0.15
    0.09
    107
    +0.12
    0.07
    Negative Logits
    ±
    -2.46
    º
    -2.36
    ¡
    -2.21
    ĸ
    -2.09
    ª
    -2.02
    ŀ
    -2.00
    ½
    -1.98
    £
    -1.97
    <|outofrange|>
    -1.93
    -1.93
    POSITIVE LOGITS
     distance
    1.67
     latency
    1.63
    ↵↵↵↵
    1.48
     discrepancy
    1.46
    haul
    1.44
     xe
    1.43
     eldest
    1.43
     disclosed
    1.43
    ↵↵
    1.43
    $]{};
    1.42
    Activations Density 2.745%

    No Known Activations