© 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. 2-MLP-SM
    11. 24104
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations related to various organizations, entities, and concepts

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    156
    +0.19
    1.1%
    23
    +0.16
    0.9%
    22
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.19
    0.04
    332
    +0.16
    0.05
    374
    +0.13
    0.01
    Negative Logits
    asone
    -1.99
    anine
    -1.77
    ovsk
    -1.77
    ţ
    -1.75
    jsfiddle
    -1.61
     {#
    -1.54
    Verlag
    -1.53
    Argued
    -1.52
    ovic
    -1.49
    ushima
    -1.49
    POSITIVE LOGITS
    Ĺ
    3.57
    ¿½
    3.33
    µ
    3.29
    ±
    3.29
    Ļ
    3.23
    «
    3.23
    °
    3.20
    ¿
    3.18
    ¨
    3.18
    ©
    3.14
    Activations Density 0.553%

    No Known Activations