© 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. 29790
    Prev
    Next
    INDEX
    Explanations

    conjunctions and repeated phrases indicating connection or continuation

    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
    405
    +0.17
    0.9%
    296
    +0.11
    0.6%
    180
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.17
    0.42
    209
    +0.11
    0.26
    402
    +0.11
    0.27
    Negative Logits
    ¾
    -4.25
    Ĥ¬
    -4.07
    ·
    -3.94
    ¶
    -3.88
    ¸
    -3.87
    ĥ
    -3.84
    ľ
    -3.80
    ı
    -3.80
    ½
    -3.78
    ļ
    -3.76
    POSITIVE LOGITS
    estry
    1.74
    nah
    1.71
    town
    1.52
     gol
    1.40
    dit
    1.36
     extinct
    1.35
     round
    1.35
    '):
    1.32
    bourne
    1.32
    bard
    1.30
    Activations Density 1.750%

    No Known Activations