© 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. 24298
    Prev
    Next
    INDEX
    Explanations

    programming-related commands and assignments

    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
    56
    +0.15
    0.8%
    271
    +0.14
    0.8%
    430
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.15
    0.06
    38
    +0.14
    0.01
    279
    +0.12
    0.04
    Negative Logits
    ĥ½
    -1.61
    romycin
    -1.56
     together
    -1.49
    rency
    -1.45
     Charge
    -1.37
     consec
    -1.37
     electroph
    -1.37
     signatures
    -1.36
     Electron
    -1.36
     msgid
    -1.35
    POSITIVE LOGITS
    another
    1.67
    style
    1.67
     another
    1.59
    use
    1.56
     sake
    1.50
    uses
    1.49
    bert
    1.48
    what
    1.47
    place
    1.44
     horizon
    1.41
    Activations Density 0.340%

    No Known Activations