© 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. 28068
    Prev
    Next
    INDEX
    Explanations

    terms related to security concerns

    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
    86
    +0.15
    0.9%
    16
    +0.12
    0.7%
    306
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.15
    0.04
    16
    +0.12
    0.03
    312
    +0.11
    0.03
    Negative Logits
    ĥ½
    -2.58
    »
    -2.57
    ¹
    -2.56
    ¿
    -2.44
    ¸
    -2.37
    Ļª
    -2.34
    ·
    -2.34
    Į
    -2.29
    ĨĴ
    -2.25
    ·¸
    -2.15
    POSITIVE LOGITS
    holes
    1.88
     surrounds
    1.79
     holes
    1.77
    birds
    1.71
    ious
    1.71
     flaws
    1.70
     clearance
    1.68
    ificial
    1.66
    hole
    1.64
     hole
    1.64
    Activations Density 0.023%

    No Known Activations