© 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. 25607
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to privacy policies

    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
    382
    +0.14
    0.8%
    23
    +0.14
    0.8%
    107
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.14
    0.06
    355
    +0.14
    0.10
    364
    +0.13
    0.08
    Negative Logits
    icio
    -1.78
    ÃŃs
    -1.70
    ental
    -1.48
     environment
    -1.43
    bane
    -1.39
    ActivityThread
    -1.39
     inbox
    -1.37
    xico
    -1.36
    alian
    -1.35
    ires
    -1.34
    POSITIVE LOGITS
    ł
    2.08
    į
    2.04
    ĸ´
    2.02
    Ī
    1.93
    >`
    1.91
    Īĺ
    1.89
    ²
    1.88
    «
    1.84
    ·¸
    1.79
    Ĥ¬
    1.79
    Activations Density 2.031%

    No Known Activations