© 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. 30551
    Prev
    Next
    INDEX
    Explanations

    references to entities that produce or create

    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
    +0.16
    0.9%
    376
    +0.15
    0.8%
    407
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.16
    0.02
    44
    +0.15
    0.01
    105
    +0.15
    0.01
    Negative Logits
    unden
    -1.68
    "?"
    -1.56
    attered
    -1.51
    *](#
    -1.46
    heastern
    -1.45
    .""
    -1.42
    ented
    -1.42
    enz
    -1.39
    inher
    -1.39
    .'"
    -1.37
    POSITIVE LOGITS
    craft
    2.08
    pieces
    1.92
    ries
    1.78
    ry
    1.74
    pin
    1.74
    liness
    1.72
    ship
    1.68
     charged
    1.61
    piece
    1.54
    maid
    1.54
    Activations Density 0.025%

    No Known Activations