© 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 EvalsExportsinterp-engineNEWAPI 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. 29956
    Prev
    Next
    INDEX
    Explanations

    references to varied real-life scenarios or circumstances

    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
    156
    +0.34
    2.1%
    376
    +0.16
    1.0%
    184
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.34
    0.02
    110
    +0.16
    0.01
    156
    +0.13
    0.01
    Negative Logits
     ↵
    -3.07
    -3.07
    ↵
    -3.07
    ↵Č
    -3.07
    ↵
    -3.07
    ↵
    -3.07
    <|outofrange|>
    -3.07
    ↵
    -3.07
    č↵
    -3.07
    -3.07
    POSITIVE LOGITS
    afe
    1.56
    inator
    1.51
     diagram
    1.45
     encountered
    1.43
    osaur
    1.42
     involving
    1.42
    oon
    1.41
    idine
    1.38
     sensed
    1.38
    icle
    1.37
    Activations Density 0.015%

    No Known Activations