© 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. 28300
    Prev
    Next
    INDEX
    Explanations

    references to the name " Jong" in any context

    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
    397
    +0.15
    0.9%
    144
    +0.12
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    395
    +0.15
    0.03
    397
    +0.12
    0.02
    64
    +0.11
    0.02
    Negative Logits
    [/
    -1.46
    ctive
    -1.46
     clean
    -1.41
    atics
    -1.37
     reason
    -1.36
    oud
    -1.35
    ONS
    -1.35
    uth
    -1.33
    sev
    -1.32
    atically
    -1.31
    POSITIVE LOGITS
    ·
    1.64
    overnment
    1.62
    hearted
    1.61
    ĥ½
    1.61
    enstein
    1.57
    stock
    1.57
    ¹
    1.53
    kok
    1.53
    eson
    1.53
    lish
    1.51
    Activations Density 5.078%

    No Known Activations