© 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. 28564
    Prev
    Next
    INDEX
    Explanations

    references to the character Aquaman

    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
    369
    +0.19
    1.1%
    376
    +0.15
    0.9%
    111
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.19
    0.01
    383
    +0.15
    0.01
    1
    +0.13
    0.01
    Negative Logits
    hes
    -1.62
     shaping
    -1.60
     largest
    -1.57
     strongest
    -1.54
    ness
    -1.51
    oad
    -1.48
    oder
    -1.47
     same
    -1.45
    rap
    -1.43
    cludes
    -1.41
    POSITIVE LOGITS
    ilee
    1.88
    ibase
    1.85
    arum
    1.54
     Studios
    1.51
    iom
    1.51
    pton
    1.49
    ¤
    1.49
    ifer
    1.48
     Awards
    1.45
    ankind
    1.44
    Activations Density 0.012%

    No Known Activations