© 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. 2-MLP-SM
    11. 24431
    Prev
    Next
    INDEX
    Explanations

    references to institutions and organizations

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    23
    +0.21
    1.2%
    455
    +0.14
    0.8%
    508
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.21
    0.09
    23
    +0.14
    0.05
    466
    +0.13
    0.09
    Negative Logits
    velopment
    -1.77
    elta
    -1.63
     GmbH
    -1.59
    mann
    -1.53
    ruptcy
    -1.48
    esan
    -1.46
    mond
    -1.46
    ysis
    -1.45
     wird
    -1.45
    nement
    -1.43
    POSITIVE LOGITS
    ĥ½
    2.38
    ľĵ
    2.08
    responding
    1.87
    1.85
    ↵
    1.85
    <|outofrange|>
    1.85
    ↵
    1.85
    ↵
    1.85
    ↵
    1.85
    <|outofrange|>
    1.85
    Activations Density 2.720%

    No Known Activations