© 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. 30280
    Prev
    Next
    INDEX
    Explanations

    citations or references in the document

    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
    478
    +0.16
    0.9%
    177
    +0.14
    0.8%
    487
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.16
    0.00
    53
    +0.14
    0.04
    64
    +0.13
    0.03
    Negative Logits
    isation
    -1.69
    ization
    -1.68
     explosion
    -1.68
    IPE
    -1.51
    ysis
    -1.49
    icity
    -1.45
    /[
    -1.40
     engagement
    -1.39
    izations
    -1.37
    \*
    -1.36
    POSITIVE LOGITS
    ľĵ
    2.64
    Ķ
    2.57
    ·¸
    2.56
    ¼
    2.56
    ĻĤ
    2.48
    ģ
    2.44
    ½
    2.32
    į
    2.32
    İ
    2.28
    Īĺ
    2.26
    Activations Density 8.999%

    No Known Activations