© 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. 28395
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "Te"

    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
    457
    +0.18
    1.0%
    369
    +0.18
    1.0%
    376
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    457
    +0.18
    0.02
    77
    +0.18
    0.01
    196
    +0.17
    0.01
    Negative Logits
    Ļª
    -2.10
    ypse
    -1.94
    teenth
    -1.90
    Ł
    -1.83
    Ĺ
    -1.81
    ¥
    -1.77
    mente
    -1.72
    ly
    -1.67
    Ħ
    -1.67
    Ī
    -1.60
    POSITIVE LOGITS
    ild
    1.58
    bys
    1.50
    orian
    1.49
     read
    1.48
    ’
    1.47
     overload
    1.44
     âĢķ
    1.43
     Read
    1.41
     appeal
    1.40
    ,”
    1.40
    Activations Density 0.005%

    No Known Activations