© 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. 26802
    Prev
    Next
    INDEX
    Explanations

    the name "Al" or its variations in different 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/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
    2
    +0.17
    1.0%
    369
    +0.15
    0.8%
    475
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.17
    0.03
    475
    +0.15
    0.03
    97
    +0.11
    0.02
    Negative Logits
    disambiguation
    -1.61
     hers
    -1.51
    Īĺ
    -1.49
    Ĥ¬
    -1.49
    Ĥ
    -1.43
    WHM
    -1.42
    atically
    -1.39
     ?"
    -1.38
    iginally
    -1.38
    ALSE
    -1.34
    POSITIVE LOGITS
    thouse
    2.04
    gorithms
    1.72
    gate
    1.60
    zheimer
    1.55
    abi
    1.51
    horn
    1.50
    bery
    1.50
    gor
    1.47
    ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
    1.46
    abama
    1.45
    Activations Density 1.108%

    No Known Activations