© 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. 0-MLP-SM
    11. 26516
    Prev
    Next
    INDEX
    Explanations

    the pronoun "he."

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    25
    +0.12
    0.7%
    217
    +0.12
    0.6%
    483
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.12
    0.11
    248
    +0.12
    0.09
    295
    +0.11
    0.09
    Negative Logits
    ħ
    -2.00
    ĩ
    -1.74
     Bengal
    -1.65
     Indianapolis
    -1.56
    ľĵ
    -1.50
    Ļ
    -1.46
     lasting
    -1.45
     Delhi
    -1.45
     Bangladesh
    -1.43
    ®
    -1.42
    POSITIVE LOGITS
    ){#
    1.70
    imize
    1.60
    goto
    1.45
    cep
    1.44
    https
    1.44
    $),
    1.42
    Category
    1.42
    dess
    1.40
    ney
    1.40
    )))
    1.38
    Activations Density 0.142%

    No Known Activations