© 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. 2-MLP-SM
    11. 24081
    Prev
    Next
    INDEX
    Explanations

    references to file paths and directories

    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
    156
    +0.22
    1.2%
    23
    +0.17
    0.9%
    283
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.22
    0.02
    343
    +0.17
    0.03
    374
    +0.12
    0.00
    Negative Logits
    ?).
    -1.65
     gond
    -1.56
    etto
    -1.46
    UTERS
    -1.46
     guessing
    -1.43
    umns
    -1.42
    gio
    -1.39
    atures
    -1.36
    AndroidRuntime
    -1.35
    gni
    -1.34
    POSITIVE LOGITS
    ever
    1.60
    abol
    1.59
    .$
    1.59
     ever
    1.56
    oles
    1.39
    incorporated
    1.36
    copyright
    1.30
    Swift
    1.30
    acts
    1.29
    SM
    1.29
    Activations Density 0.392%

    No Known Activations