© 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. 23515
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical concepts and structures, particularly in relation to Ricci solitons and homogeneous spaces

    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
    232
    +0.17
    0.9%
    464
    +0.15
    0.9%
    23
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.17
    0.16
    23
    +0.15
    0.07
    460
    +0.14
    0.06
    Negative Logits
    ipeg
    -1.71
    isia
    -1.67
    lest
    -1.61
    stown
    -1.58
    gage
    -1.53
    veolar
    -1.53
    Decided
    -1.53
    agne
    -1.53
    acea
    -1.50
    atta
    -1.48
    POSITIVE LOGITS
    ¿½
    3.00
    ĻĤ
    2.44
    «
    2.36
    ¨
    2.33
    Ļª
    2.33
    °
    2.31
    ±
    2.30
    ¤
    2.29
    ³
    2.19
    ¾
    2.18
    Activations Density 1.278%

    No Known Activations