© 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 EvalsExportsAPI 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. 25311
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or administrative responsibilities

    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
    479
    +0.13
    0.7%
    309
    +0.12
    0.6%
    291
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.13
    0.05
    291
    +0.12
    0.08
    338
    +0.11
    0.05
    Negative Logits
    omb
    -1.80
    mapsto
    -1.71
    ativity
    -1.68
    coming
    -1.65
     lately
    -1.51
    éri
    -1.48
    anting
    -1.46
    ieux
    -1.45
    :'
    -1.41
    âĨĴ
    -1.40
    POSITIVE LOGITS
     Partners
    1.64
    ŀ
    1.62
    bies
    1.59
    °
    1.57
     ways
    1.56
    ±
    1.54
    devel
    1.52
     colleagues
    1.51
    IJ
    1.50
     Studios
    1.43
    Activations Density 0.753%

    No Known Activations