© 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. 26315
    Prev
    Next
    INDEX
    Explanations

    references to braces and brackets in text, indicating structure or syntax

    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
    106
    +0.18
    1.0%
    362
    +0.13
    0.7%
    258
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.18
    0.01
    158
    +0.13
    0.01
    247
    +0.12
    0.01
    Negative Logits
    )](
    -1.43
     coincide
    -1.42
     visit
    -1.40
     specific
    -1.40
    arer
    -1.37
     sites
    -1.37
     Consortium
    -1.37
    rons
    -1.32
     GHz
    -1.32
    icki
    -1.32
    POSITIVE LOGITS
    uity
    1.95
    wolf
    1.63
    wordpress
    1.56
     wondering
    1.51
     probably
    1.48
     expectancy
    1.47
     damn
    1.42
    woke
    1.41
    hum
    1.40
    chapter
    1.37
    Activations Density 0.077%

    No Known Activations