© 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. 0-MLP-SM
    11. 29135
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" used to connect multiple ideas or elements within the text

    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
    262
    +0.15
    0.8%
    237
    +0.11
    0.6%
    320
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.15
    0.45
    209
    +0.11
    0.29
    402
    +0.11
    0.26
    Negative Logits
    ĩ
    -1.95
     legend
    -1.49
    ingly
    -1.46
     lane
    -1.38
    belt
    -1.36
    LLY
    -1.35
    way
    -1.34
    ↵³³
    -1.34
    ographer
    -1.34
     deserve
    -1.33
    POSITIVE LOGITS
    hes
    2.04
    hers
    1.47
    hering
    1.38
    hest
    1.37
    hus
    1.37
    urs
    1.35
    ://
    1.34
    oint
    1.34
    ryst
    1.32
    patcher
    1.30
    Activations Density 1.576%

    No Known Activations