© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 28462
    Prev
    Next
    INDEX
    Explanations

    the word "conserv" in various contexts indicating conservative viewpoints or actions

    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
    111
    +0.12
    0.7%
    316
    +0.12
    0.7%
    126
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.01
    126
    +0.12
    0.01
    316
    +0.11
    0.01
    Negative Logits
    ĨĴ
    -3.09
    »¿
    -2.84
    ¹
    -2.79
    ↵
    -2.77
    -2.77
    ↵
    -2.77
    ↵
    -2.77
     ↵
    -2.77
    <|outofrange|>
    -2.77
    ↵
    -2.77
    POSITIVE LOGITS
    es
    1.55
    engers
    1.52
    atories
    1.48
    atism
    1.46
    bard
    1.43
    arts
    1.41
    isite
    1.41
    iences
    1.39
    ested
    1.36
    ettes
    1.35
    Activations Density 0.016%

    No Known Activations