© 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. 25932
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'compared'

    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
    376
    +0.18
    1.0%
    148
    +0.15
    0.9%
    485
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    342
    +0.18
    0.03
    212
    +0.15
    0.02
    14
    +0.11
    0.02
    Negative Logits
    ľ
    -2.15
    Ŀ
    -1.96
    º
    -1.91
    Ļ
    -1.86
    ĸ
    -1.86
    »
    -1.86
    ´
    -1.78
    Ĵ
    -1.75
    ¸
    -1.71
    »¿
    -1.70
    POSITIVE LOGITS
     favorably
    1.83
    uar
    1.79
     with
    1.70
    feit
    1.68
    igraphy
    1.67
    agon
    1.63
    ger
    1.60
     thereto
    1.58
    cif
    1.49
     thereon
    1.47
    Activations Density 0.013%

    No Known Activations