© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-MLP-SM
    11. 27068
    Prev
    Next
    INDEX
    Explanations

    assertions of strong opinions

    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
    38
    +0.11
    0.6%
    65
    +0.11
    0.6%
    419
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.11
    0.39
    53
    +0.11
    0.41
    56
    +0.11
    0.10
    Negative Logits
    ½
    -3.53
    ĭ
    -3.52
    ®
    -3.46
    °
    -3.35
    Ī
    -3.33
    ¤
    -3.31
    Į
    -3.26
    ¥
    -3.23
    ¼
    -3.23
    Ħ
    -3.21
    POSITIVE LOGITS
    roads
    1.65
    pieces
    1.55
    cules
    1.55
    sets
    1.54
    iÄĩ
    1.51
    aday
    1.47
    inals
    1.46
     sooner
    1.46
    fellow
    1.45
    nail
    1.43
    Activations Density 4.755%

    No Known Activations