© 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. 26810
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation marks or special characters

    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
    115
    +0.18
    1.0%
    478
    +0.17
    1.0%
    23
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.18
    0.01
    5
    +0.17
    0.01
    278
    +0.16
    0.02
    Negative Logits
    ys
    -1.74
    cript
    -1.73
    ics
    -1.67
    azine
    -1.57
    ostat
    -1.53
    os
    -1.51
    eller
    -1.48
    hardt
    -1.48
    eral
    -1.48
    urn
    -1.45
    POSITIVE LOGITS
    ¼
    3.31
    º
    3.25
    Ĭ
    3.00
    Ŀ
    2.96
    Ĵ
    2.96
    Ģ
    2.82
    ı
    2.78
    ľ
    2.72
    ¸
    2.72
    Ĥ
    2.71
    Activations Density 0.009%

    No Known Activations