© 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. 23057
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic or administrative districts

    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
    23
    +0.23
    1.3%
    420
    +0.13
    0.7%
    162
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.23
    0.02
    162
    +0.13
    0.03
    420
    +0.10
    0.02
    Negative Logits
    ĻĤ
    -1.89
    ¾
    -1.80
     forums
    -1.65
     Awards
    -1.63
     licenses
    -1.63
    ements
    -1.60
     petitions
    -1.57
     (.
    -1.56
    heets
    -1.49
     Biosciences
    -1.48
    POSITIVE LOGITS
    "}](#
    1.91
    effect
    1.78
     time
    1.71
    wards
    1.63
    argin
    1.60
    character
    1.56
    between
    1.56
    then
    1.52
    isin
    1.51
     operator
    1.49
    Activations Density 0.242%

    No Known Activations