© 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. 24039
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "and" in various contexts

    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
    416
    +0.12
    0.7%
    27
    +0.12
    0.6%
    500
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.12
    0.04
    416
    +0.12
    0.06
    27
    +0.11
    0.03
    Negative Logits
    à±į
    -1.73
    ocalypse
    -1.72
    éri
    -1.70
    uto
    -1.62
    esto
    -1.59
    à¯ģ
    -1.57
    initis
    -1.54
    inyl
    -1.52
    ி
    -1.51
    acts
    -1.51
    POSITIVE LOGITS
     liking
    1.51
     personally
    1.45
     eg
    1.39
     humor
    1.37
    kubuntu
    1.36
     ourselves
    1.34
    naments
    1.33
     colleagues
    1.33
     even
    1.33
     eyebrows
    1.31
    Activations Density 0.220%

    No Known Activations