© 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. 27037
    Prev
    Next
    INDEX
    Explanations

    the mention of the term "Alden" in various contexts

    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
    369
    +0.27
    1.6%
    59
    +0.14
    0.8%
    2
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.27
    0.01
    369
    +0.14
    0.01
    2
    +0.12
    0.01
    Negative Logits
    Ļª
    -2.00
    ĵ
    -1.93
    IJ
    -1.91
    Ĺ
    -1.66
    ↵
    -1.64
    <|outofrange|>
    -1.64
    ↵↵
    -1.64
    -1.64
    -1.64
    <|outofrange|>
    -1.64
    POSITIVE LOGITS
    enstein
    1.72
    osterone
    1.69
    uet
    1.69
    gated
    1.67
    anyl
    1.64
    erp
    1.64
    leneck
    1.62
    wyn
    1.60
    estock
    1.60
    isecond
    1.59
    Activations Density 0.011%

    No Known Activations